def test_predict_mocked(self, rf_mock):
class SideEffect(object):
def __init__(self):
self.counter = 0
def __call__(self, X):
self.counter += 1
# Mean and variance
rval = np.array([self.counter] * X.shape[0])
return rval, rval
rf_mock.side_effect = SideEffect()
rs = np.random.RandomState(1)
X = rs.rand(20, 10)
Y = rs.rand(10, 3)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'ln(runtime)', 'foo'], np.zeros((10, ), dtype=np.uint))
model.train(X[:10], Y[:10])
m_hat, v_hat = model.predict(X[10:])
self.assertEqual(m_hat.shape, (10, 3))
self.assertEqual(v_hat.shape, (10, 3))
self.assertEqual(rf_mock.call_count, 3)
for i in range(10):
for j in range(3):
self.assertEqual(m_hat[i][j], j + 1)
self.assertEqual(v_hat[i][j], j + 1)
def test_train_and_predict_with_rf(self):
rs = np.random.RandomState(1)
X = rs.rand(20, 10)
Y = rs.rand(10, 2)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'ln(runtime)'], np.zeros((10, ), dtype=np.uint))
model.train(X[:10], Y)
m, v = model.predict(X[10:])
self.assertEqual(m.shape, (10, 2))
self.assertEqual(v.shape, (10, 2))
def test_train_and_predict_with_rf(self):
rs = np.random.RandomState(1)
X = rs.rand(20, 10)
Y = rs.rand(10, 2)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'ln(runtime)'],
types=np.zeros((10, ), dtype=np.uint),
bounds=np.array([(0, np.nan), (0, np.nan), (0, np.nan),
(0, np.nan), (0, np.nan), (0, np.nan),
(0, np.nan), (0, np.nan), (0, np.nan),
(0, np.nan)],
dtype=object),
rf_kwargs={'seed': 1},
pca_components=5)
self.assertEqual(model.estimators[0].seed, 1)
self.assertEqual(model.estimators[1].seed, 1)
self.assertEqual(model.pca_components, 5)
model.train(X[:10], Y)
m, v = model.predict(X[10:])
self.assertEqual(m.shape, (10, 2))
self.assertEqual(v.shape, (10, 2))
def test_init_EIPS_as_arguments(self):
for objective in ['runtime', 'quality']:
self.scenario.run_obj = objective
types, bounds = get_types(self.scenario.cs, None)
umrfwi = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'runtime'], types, bounds)
eips = EIPS(umrfwi)
rh2EPM = RunHistory2EPM4EIPS(self.scenario, 2)
smbo = SMAC(self.scenario, model=umrfwi, acquisition_function=eips,
runhistory2epm=rh2EPM).solver
self.assertIs(umrfwi, smbo.model)
self.assertIs(eips, smbo.acquisition_func)
self.assertIs(rh2EPM, smbo.rh2EPM)
def test_eips(self):
scenario = Scenario({'cs': test_helpers.get_branin_config_space(),
'run_obj': 'quality',
'deterministic': True,
'output_dir': ''})
types = get_types(scenario.cs, None)
umrfwi = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'runtime'], types)
eips = EIPS(umrfwi)
rh2EPM = RunHistory2EPM4EIPS(scenario, 2)
taf = ExecuteTAFunc(test_function)
smbo = SMBO(scenario, model=umrfwi, acquisition_function=eips,
runhistory2epm=rh2EPM, tae_runner=taf,
random_configuration_chooser=ChooserNoCoolDown(2.0))
smbo.run(5)
print(smbo.incumbent)
raise ValueError()
def get_eips_object_callback(
scenario_dict,
seed,
ta,
backend,
metalearning_configurations,
runhistory,
):
scenario_dict['input_psmac_dirs'] = backend.get_smac_output_glob()
scenario = Scenario(scenario_dict)
rh2EPM = RunHistory2EPM4EIPS(
num_params=len(scenario.cs.get_hyperparameters()),
scenario=scenario,
success_states=[
StatusType.SUCCESS,
StatusType.MEMOUT,
StatusType.TIMEOUT,
StatusType.CRASHED
],
impute_censored_data=False,
impute_state=None
)
types, bounds = get_types(scenario.cs,
scenario.feature_array)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'runtime'],
types=types,
bounds=bounds,
instance_features=scenario.feature_array,
rf_kwargs={'seed': 1,},
)
acquisition_function = EIPS(model)
return SMAC(
runhistory=runhistory,
scenario=scenario,
rng=seed,
tae_runner=ta,
runhistory2epm=rh2EPM,
model=model,
acquisition_function=acquisition_function,
run_id=seed,
)
def run_smbo(self, max_iters=1000):
global evaluator
# == first things first: load the datamanager
self.reset_data_manager()
# == Initialize SMBO stuff
# first create a scenario
seed = self.seed # TODO
num_params = len(self.config_space.get_hyperparameters())
# allocate a run history
run_history = RunHistory()
meta_runhistory = RunHistory()
meta_runs_dataset_indices = {}
num_run = self.start_num_run
instance_id = self.dataset_name + SENTINEL
# == Train on subset
# before doing anything, let us run the default_cfg
# on a subset of the available data to ensure that
# we at least have some models
# we will try three different ratios of decreasing magnitude
# in the hope that at least on the last one we will be able
# to get a model
n_data = self.datamanager.data['X_train'].shape[0]
subset_ratio = 10000. / n_data
if subset_ratio >= 0.5:
subset_ratio = 0.33
subset_ratios = [subset_ratio, subset_ratio * 0.10]
else:
subset_ratios = [subset_ratio, 500. / n_data]
self.logger.info("Training default configurations on a subset of "
"%d/%d data points." %
(int(n_data * subset_ratio), n_data))
# the time limit for these function evaluations is rigorously
# set to only 1/2 of a full function evaluation
subset_time_limit = max(5, int(self.func_eval_time_limit / 2))
# the configs we want to run on the data subset are:
# 1) the default configs
# 2) a set of configs we selected for training on a subset
subset_configs = [self.config_space.get_default_configuration()] \
+ self.collect_additional_subset_defaults()
subset_config_succesful = [False] * len(subset_configs)
for subset_config_id, next_config in enumerate(subset_configs):
for i, ratio in enumerate(subset_ratios):
self.reset_data_manager()
n_data_subsample = int(n_data * ratio)
# run the config, but throw away the result afterwards
# since this cfg was evaluated only on a subset
# and we don't want to confuse SMAC
self.logger.info(
"Starting to evaluate %d on SUBSET "
"with size %d and time limit %ds.", num_run,
n_data_subsample, subset_time_limit)
self.logger.info(next_config)
_info = eval_with_limits(self.datamanager, self.tmp_dir,
next_config, seed, num_run,
self.resampling_strategy,
self.resampling_strategy_args,
self.memory_limit, subset_time_limit,
n_data_subsample)
(duration, result, _, additional_run_info, status) = _info
self.logger.info(
"Finished evaluating %d. configuration on SUBSET. "
"Duration %f; loss %f; status %s; additional run "
"info: %s ", num_run, duration, result, str(status),
additional_run_info)
num_run += 1
if i < len(subset_ratios) - 1:
if status != StatusType.SUCCESS:
# Do not increase num_run here, because we will try
# the same configuration with less data
self.logger.info(
"A CONFIG did not finish "
" for subset ratio %f -> going smaller", ratio)
continue
else:
self.logger.info(
"Finished SUBSET training sucessfully "
"with ratio %f", ratio)
subset_config_succesful[subset_config_id] = True
break
else:
if status != StatusType.SUCCESS:
self.logger.info(
"A CONFIG did not finish "
" for subset ratio %f.", ratio)
continue
else:
self.logger.info(
"Finished SUBSET training sucessfully "
"with ratio %f", ratio)
subset_config_succesful[subset_config_id] = True
break
# Use the first non-failing configuration from the subsets as the new
# default configuration -> this guards us against the random forest
# failing on large, sparse datasets
default_cfg = None
for subset_config_id, next_config in enumerate(subset_configs):
if subset_config_succesful[subset_config_id]:
default_cfg = next_config
break
if default_cfg is None:
default_cfg = self.config_space.get_default_configuration()
# == METALEARNING suggestions
# we start by evaluating the defaults on the full dataset again
# and add the suggestions from metalearning behind it
if self.metadata_directory is None:
metalearning_directory = os.path.dirname(
autosklearn.metalearning.__file__)
# There is no multilabel data in OpenML
if self.task == MULTILABEL_CLASSIFICATION:
meta_task = BINARY_CLASSIFICATION
else:
meta_task = self.task
metadata_directory = os.path.join(
metalearning_directory, 'files', '%s_%s_%s' %
(METRIC_TO_STRING[self.metric],
TASK_TYPES_TO_STRING[meta_task],
'sparse' if self.datamanager.info['is_sparse'] else 'dense'))
self.metadata_directory = metadata_directory
self.logger.info('Metadata directory: %s', self.metadata_directory)
meta_base = MetaBase(self.config_space, self.metadata_directory)
metafeature_calculation_time_limit = int(self.total_walltime_limit / 4)
metafeature_calculation_start_time = time.time()
meta_features = self._calculate_metafeatures_with_limits(
metafeature_calculation_time_limit)
metafeature_calculation_end_time = time.time()
metafeature_calculation_time_limit = \
metafeature_calculation_time_limit - (
metafeature_calculation_end_time -
metafeature_calculation_start_time)
if metafeature_calculation_time_limit < 1:
self.logger.warning(
'Time limit for metafeature calculation less '
'than 1 seconds (%f). Skipping calculation '
'of metafeatures for encoded dataset.',
metafeature_calculation_time_limit)
meta_features_encoded = None
else:
self.datamanager.perform1HotEncoding()
meta_features_encoded = \
self._calculate_metafeatures_encoded_with_limits(
metafeature_calculation_time_limit)
# In case there is a problem calculating the encoded meta-features
if meta_features is None:
if meta_features_encoded is not None:
meta_features = meta_features_encoded
else:
if meta_features_encoded is not None:
meta_features.metafeature_values.update(
meta_features_encoded.metafeature_values)
if meta_features is not None:
meta_base.add_dataset(instance_id, meta_features)
# Do mean imputation of the meta-features - should be done specific
# for each prediction model!
all_metafeatures = meta_base.get_metafeatures(
features=list(meta_features.keys()))
all_metafeatures.fillna(all_metafeatures.mean(), inplace=True)
metalearning_configurations = self.collect_metalearning_suggestions(
meta_base)
if metalearning_configurations is None:
metalearning_configurations = []
self.reset_data_manager()
self.logger.info('%s', meta_features)
# Convert meta-features into a dictionary because the scenario
# expects a dictionary
meta_features_dict = {}
for dataset, series in all_metafeatures.iterrows():
meta_features_dict[dataset] = series.values
meta_features_list = []
for meta_feature_name in all_metafeatures.columns:
meta_features_list.append(
meta_features[meta_feature_name].value)
meta_features_list = np.array(meta_features_list).reshape((1, -1))
self.logger.info(list(meta_features_dict.keys()))
meta_runs = meta_base.get_all_runs(METRIC_TO_STRING[self.metric])
meta_runs_index = 0
try:
meta_durations = meta_base.get_all_runs('runtime')
read_runtime_data = True
except KeyError:
read_runtime_data = False
self.logger.critical('Cannot read runtime data.')
if self.acquisition_function == 'EIPS':
self.logger.critical(
'Reverting to acquisition function EI!')
self.acquisition_function = 'EI'
for meta_dataset in meta_runs.index:
meta_dataset_start_index = meta_runs_index
for meta_configuration in meta_runs.columns:
if np.isfinite(meta_runs.loc[meta_dataset,
meta_configuration]):
try:
config = meta_base.get_configuration_from_algorithm_index(
meta_configuration)
cost = meta_runs.loc[meta_dataset,
meta_configuration]
if read_runtime_data:
runtime = meta_durations.loc[
meta_dataset, meta_configuration]
else:
runtime = 1
# TODO read out other status types!
meta_runhistory.add(config,
cost,
runtime,
StatusType.SUCCESS,
instance_id=meta_dataset)
meta_runs_index += 1
except:
# TODO maybe add warning
pass
meta_runs_dataset_indices[meta_dataset] = (
meta_dataset_start_index, meta_runs_index)
else:
if self.acquisition_function == 'EIPS':
self.logger.critical('Reverting to acquisition function EI!')
self.acquisition_function = 'EI'
meta_features_list = []
meta_features_dict = {}
metalearning_configurations = []
self.scenario = AutoMLScenario(self.config_space,
self.total_walltime_limit,
self.func_eval_time_limit,
meta_features_dict, self.tmp_dir,
self.shared_mode)
types = get_types(self.config_space, self.scenario.feature_array)
if self.acquisition_function == 'EI':
rh2EPM = RunHistory2EPM4Cost(num_params=num_params,
scenario=self.scenario,
success_states=None,
impute_censored_data=False,
impute_state=None)
model = RandomForestWithInstances(
types,
instance_features=meta_features_list,
seed=1,
num_trees=10)
smac = SMBO(self.scenario, model=model, rng=seed)
elif self.acquisition_function == 'EIPS':
rh2EPM = RunHistory2EPM4EIPS(num_params=num_params,
scenario=self.scenario,
success_states=None,
impute_censored_data=False,
impute_state=None)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'runtime'],
types,
num_trees=10,
instance_features=meta_features_list,
seed=1)
acquisition_function = EIPS(model)
smac = SMBO(self.scenario,
acquisition_function=acquisition_function,
model=model,
runhistory2epm=rh2EPM,
rng=seed)
else:
raise ValueError('Unknown acquisition function value %s!' %
self.acquisition_function)
# Build a runtime model
# runtime_rf = RandomForestWithInstances(types,
# instance_features=meta_features_list,
# seed=1, num_trees=10)
# runtime_rh2EPM = RunHistory2EPM4EIPS(num_params=num_params,
# scenario=self.scenario,
# success_states=None,
# impute_censored_data=False,
# impute_state=None)
# X_runtime, y_runtime = runtime_rh2EPM.transform(meta_runhistory)
# runtime_rf.train(X_runtime, y_runtime[:, 1].flatten())
X_meta, Y_meta = rh2EPM.transform(meta_runhistory)
# Transform Y_meta on a per-dataset base
for meta_dataset in meta_runs_dataset_indices:
start_index, end_index = meta_runs_dataset_indices[meta_dataset]
end_index += 1 # Python indexing
Y_meta[start_index:end_index, 0]\
[Y_meta[start_index:end_index, 0] >2.0] = 2.0
dataset_minimum = np.min(Y_meta[start_index:end_index, 0])
Y_meta[start_index:end_index,
0] = 1 - ((1. - Y_meta[start_index:end_index, 0]) /
(1. - dataset_minimum))
Y_meta[start_index:end_index, 0]\
[Y_meta[start_index:end_index, 0] > 2] = 2
# == first, evaluate all metelearning and default configurations
for i, next_config in enumerate(
([default_cfg] + metalearning_configurations)):
# Do not evaluate default configurations more than once
if i >= len([default_cfg]) and next_config in [default_cfg]:
continue
config_name = 'meta-learning' if i >= len([default_cfg]) \
else 'default'
self.logger.info(
"Starting to evaluate %d. configuration "
"(%s configuration) with time limit %ds.", num_run,
config_name, self.func_eval_time_limit)
self.logger.info(next_config)
self.reset_data_manager()
info = eval_with_limits(self.datamanager, self.tmp_dir,
next_config, seed, num_run,
self.resampling_strategy,
self.resampling_strategy_args,
self.memory_limit,
self.func_eval_time_limit)
(duration, result, _, additional_run_info, status) = info
run_history.add(config=next_config,
cost=result,
time=duration,
status=status,
instance_id=instance_id,
seed=seed)
run_history.update_cost(next_config, result)
self.logger.info(
"Finished evaluating %d. configuration. "
"Duration %f; loss %f; status %s; additional run "
"info: %s ", num_run, duration, result, str(status),
additional_run_info)
num_run += 1
if smac.incumbent is None:
smac.incumbent = next_config
elif result < run_history.get_cost(smac.incumbent):
smac.incumbent = next_config
if self.scenario.shared_model:
pSMAC.write(run_history=run_history,
output_directory=self.scenario.output_dir,
num_run=self.seed)
# == after metalearning run SMAC loop
smac.runhistory = run_history
smac_iter = 0
finished = False
while not finished:
if self.scenario.shared_model:
pSMAC.read(run_history=run_history,
output_directory=self.scenario.output_dir,
configuration_space=self.config_space,
logger=self.logger)
next_configs = []
time_for_choose_next = -1
try:
X_cfg, Y_cfg = rh2EPM.transform(run_history)
if not run_history.empty():
# Update costs by normalization
dataset_minimum = np.min(Y_cfg[:, 0])
Y_cfg[:, 0] = 1 - ((1. - Y_cfg[:, 0]) /
(1. - dataset_minimum))
Y_cfg[:, 0][Y_cfg[:, 0] > 2] = 2
if len(X_meta) > 0 and len(X_cfg) > 0:
pass
#X_cfg = np.concatenate((X_meta, X_cfg))
#Y_cfg = np.concatenate((Y_meta, Y_cfg))
elif len(X_meta) > 0:
X_cfg = X_meta.copy()
Y_cfg = Y_meta.copy()
elif len(X_cfg) > 0:
X_cfg = X_cfg.copy()
Y_cfg = Y_cfg.copy()
else:
raise ValueError(
'No training data for SMAC random forest!')
self.logger.info('Using %d training points for SMAC.' %
X_cfg.shape[0])
choose_next_start_time = time.time()
next_configs_tmp = smac.choose_next(
X_cfg,
Y_cfg,
num_interleaved_random=110,
num_configurations_by_local_search=10,
num_configurations_by_random_search_sorted=100)
time_for_choose_next = time.time() - choose_next_start_time
self.logger.info('Used %g seconds to find next '
'configurations' % (time_for_choose_next))
next_configs.extend(next_configs_tmp)
# TODO put Exception here!
except Exception as e:
self.logger.error(e)
self.logger.error("Error in getting next configurations "
"with SMAC. Using random configuration!")
next_config = self.config_space.sample_configuration()
next_configs.append(next_config)
models_fitted_this_iteration = 0
start_time_this_iteration = time.time()
for next_config in next_configs:
x_runtime = impute_inactive_values(next_config)
x_runtime = impute_inactive_values(x_runtime).get_array()
# predicted_runtime = runtime_rf.predict_marginalized_over_instances(
# x_runtime.reshape((1, -1)))
# predicted_runtime = np.exp(predicted_runtime[0][0][0]) - 1
self.logger.info(
"Starting to evaluate %d. configuration (from "
"SMAC) with time limit %ds.", num_run,
self.func_eval_time_limit)
self.logger.info(next_config)
self.reset_data_manager()
info = eval_with_limits(self.datamanager, self.tmp_dir,
next_config, seed, num_run,
self.resampling_strategy,
self.resampling_strategy_args,
self.memory_limit,
self.func_eval_time_limit)
(duration, result, _, additional_run_info, status) = info
run_history.add(config=next_config,
cost=result,
time=duration,
status=status,
instance_id=instance_id,
seed=seed)
run_history.update_cost(next_config, result)
#self.logger.info('Predicted runtime %g, true runtime %g',
# predicted_runtime, duration)
# TODO add unittest to make sure everything works fine and
# this does not get outdated!
if smac.incumbent is None:
smac.incumbent = next_config
elif result < run_history.get_cost(smac.incumbent):
smac.incumbent = next_config
self.logger.info(
"Finished evaluating %d. configuration. "
"Duration: %f; loss: %f; status %s; additional "
"run info: %s ", num_run, duration, result, str(status),
additional_run_info)
smac_iter += 1
num_run += 1
models_fitted_this_iteration += 1
time_used_this_iteration = time.time(
) - start_time_this_iteration
if models_fitted_this_iteration >= 2 and \
time_for_choose_next > 0 and \
time_used_this_iteration > time_for_choose_next:
break
elif time_for_choose_next <= 0 and \
models_fitted_this_iteration >= 1:
break
elif models_fitted_this_iteration >= 50:
break
if max_iters is not None:
finished = (smac_iter < max_iters)
if self.scenario.shared_model:
pSMAC.write(run_history=run_history,
output_directory=self.scenario.output_dir,
num_run=self.seed)
def run_smbo(self):
self.watcher.start_task('SMBO')
# == first things first: load the datamanager
self.reset_data_manager()
# == Initialize non-SMBO stuff
# first create a scenario
seed = self.seed
self.config_space.seed(seed)
num_params = len(self.config_space.get_hyperparameters())
# allocate a run history
num_run = self.start_num_run
instance_id = self.dataset_name + SENTINEL
# Initialize some SMAC dependencies
runhistory = RunHistory(aggregate_func=average_cost)
# meta_runhistory = RunHistory(aggregate_func=average_cost)
# meta_runs_dataset_indices = {}
# == METALEARNING suggestions
# we start by evaluating the defaults on the full dataset again
# and add the suggestions from metalearning behind it
if self.num_metalearning_cfgs > 0:
if self.metadata_directory is None:
metalearning_directory = os.path.dirname(
autosklearn.metalearning.__file__)
# There is no multilabel data in OpenML
if self.task == MULTILABEL_CLASSIFICATION:
meta_task = BINARY_CLASSIFICATION
else:
meta_task = self.task
metadata_directory = os.path.join(
metalearning_directory, 'files', '%s_%s_%s' %
(METRIC_TO_STRING[self.metric],
TASK_TYPES_TO_STRING[meta_task], 'sparse'
if self.datamanager.info['is_sparse'] else 'dense'))
self.metadata_directory = metadata_directory
self.logger.info('Metadata directory: %s', self.metadata_directory)
meta_base = MetaBase(self.config_space, self.metadata_directory)
metafeature_calculation_time_limit = int(
self.total_walltime_limit / 4)
metafeature_calculation_start_time = time.time()
meta_features = self._calculate_metafeatures_with_limits(
metafeature_calculation_time_limit)
metafeature_calculation_end_time = time.time()
metafeature_calculation_time_limit = \
metafeature_calculation_time_limit - (
metafeature_calculation_end_time -
metafeature_calculation_start_time)
if metafeature_calculation_time_limit < 1:
self.logger.warning(
'Time limit for metafeature calculation less '
'than 1 seconds (%f). Skipping calculation '
'of metafeatures for encoded dataset.',
metafeature_calculation_time_limit)
meta_features_encoded = None
else:
with warnings.catch_warnings():
warnings.showwarning = self._send_warnings_to_log
self.datamanager.perform1HotEncoding()
meta_features_encoded = \
self._calculate_metafeatures_encoded_with_limits(
metafeature_calculation_time_limit)
# In case there is a problem calculating the encoded meta-features
if meta_features is None:
if meta_features_encoded is not None:
meta_features = meta_features_encoded
else:
if meta_features_encoded is not None:
meta_features.metafeature_values.update(
meta_features_encoded.metafeature_values)
if meta_features is not None:
meta_base.add_dataset(instance_id, meta_features)
# Do mean imputation of the meta-features - should be done specific
# for each prediction model!
all_metafeatures = meta_base.get_metafeatures(
features=list(meta_features.keys()))
all_metafeatures.fillna(all_metafeatures.mean(), inplace=True)
with warnings.catch_warnings():
warnings.showwarning = self._send_warnings_to_log
metalearning_configurations = self.collect_metalearning_suggestions(
meta_base)
if metalearning_configurations is None:
metalearning_configurations = []
self.reset_data_manager()
self.logger.info('%s', meta_features)
# Convert meta-features into a dictionary because the scenario
# expects a dictionary
meta_features_dict = {}
for dataset, series in all_metafeatures.iterrows():
meta_features_dict[dataset] = series.values
meta_features_list = []
for meta_feature_name in all_metafeatures.columns:
meta_features_list.append(
meta_features[meta_feature_name].value)
meta_features_list = np.array(meta_features_list).reshape(
(1, -1))
self.logger.info(list(meta_features_dict.keys()))
# meta_runs = meta_base.get_all_runs(METRIC_TO_STRING[self.metric])
# meta_runs_index = 0
# try:
# meta_durations = meta_base.get_all_runs('runtime')
# read_runtime_data = True
# except KeyError:
# read_runtime_data = False
# self.logger.critical('Cannot read runtime data.')
# if self.acquisition_function == 'EIPS':
# self.logger.critical('Reverting to acquisition function EI!')
# self.acquisition_function = 'EI'
# for meta_dataset in meta_runs.index:
# meta_dataset_start_index = meta_runs_index
# for meta_configuration in meta_runs.columns:
# if np.isfinite(meta_runs.loc[meta_dataset, meta_configuration]):
# try:
# config = meta_base.get_configuration_from_algorithm_index(
# meta_configuration)
# cost = meta_runs.loc[meta_dataset, meta_configuration]
# if read_runtime_data:
# runtime = meta_durations.loc[meta_dataset,
# meta_configuration]
# else:
# runtime = 1
# # TODO read out other status types!
# meta_runhistory.add(config, cost, runtime,
# StatusType.SUCCESS,
# instance_id=meta_dataset)
# meta_runs_index += 1
# except:
# # TODO maybe add warning
# pass
#
# meta_runs_dataset_indices[meta_dataset] = (
# meta_dataset_start_index, meta_runs_index)
else:
meta_features = None
if meta_features is None:
if self.acquisition_function == 'EIPS':
self.logger.critical('Reverting to acquisition function EI!')
self.acquisition_function = 'EI'
meta_features_list = []
meta_features_dict = {}
metalearning_configurations = []
if self.resampling_strategy in [
'partial-cv', 'partial-cv-iterative-fit'
]:
num_folds = self.resampling_strategy_args['folds']
instances = [[fold_number] for fold_number in range(num_folds)]
else:
instances = None
startup_time = self.watcher.wall_elapsed(self.dataset_name)
total_walltime_limit = self.total_walltime_limit - startup_time - 5
scenario_dict = {
'cs': self.config_space,
'cutoff-time': self.func_eval_time_limit,
'memory-limit': self.memory_limit,
'wallclock-limit': total_walltime_limit,
# 'instances': [[name] for name in meta_features_dict],
'output-dir': self.backend.temporary_directory,
'shared-model': self.shared_mode,
'run-obj': 'quality',
'deterministic': 'true',
'instances': instances
}
if self.configuration_mode == 'RANDOM':
scenario_dict['minR'] = len(
instances) if instances is not None else 1
scenario_dict['initial_incumbent'] = 'RANDOM'
self.scenario = Scenario(scenario_dict)
# TODO rebuild target algorithm to be it's own target algorithm
# evaluator, which takes into account that a run can be killed prior
# to the model being fully fitted; thus putting intermediate results
# into a queue and querying them once the time is over
exclude = dict()
include = dict()
if self.include_preprocessors is not None and \
self.exclude_preprocessors is not None:
raise ValueError('Cannot specify include_preprocessors and '
'exclude_preprocessors.')
elif self.include_preprocessors is not None:
include['preprocessor'] = self.include_preprocessors
elif self.exclude_preprocessors is not None:
exclude['preprocessor'] = self.exclude_preprocessors
if self.include_estimators is not None and \
self.exclude_preprocessors is not None:
raise ValueError('Cannot specify include_estimators and '
'exclude_estimators.')
elif self.include_estimators is not None:
if self.task in CLASSIFICATION_TASKS:
include['classifier'] = self.include_estimators
elif self.task in REGRESSION_TASKS:
include['regressor'] = self.include_estimators
else:
raise ValueError(self.task)
elif self.exclude_estimators is not None:
if self.task in CLASSIFICATION_TASKS:
exclude['classifier'] = self.exclude_estimators
elif self.task in REGRESSION_TASKS:
exclude['regressor'] = self.exclude_estimators
else:
raise ValueError(self.task)
ta = ExecuteTaFuncWithQueue(
backend=self.backend,
autosklearn_seed=seed,
resampling_strategy=self.resampling_strategy,
initial_num_run=num_run,
logger=self.logger,
include=include,
exclude=exclude,
memory_limit=self.memory_limit,
disable_file_output=self.disable_file_output,
**self.resampling_strategy_args)
types = get_types(self.config_space, self.scenario.feature_array)
# TODO extract generation of SMAC object into it's own function for
# testing
if self.acquisition_function == 'EI':
model = RandomForestWithInstances(
types,
#instance_features=meta_features_list,
seed=1,
num_trees=10)
rh2EPM = RunHistory2EPM4Cost(num_params=num_params,
scenario=self.scenario,
success_states=[
StatusType.SUCCESS,
StatusType.MEMOUT,
StatusType.TIMEOUT
],
impute_censored_data=False,
impute_state=None)
_smac_arguments = dict(scenario=self.scenario,
model=model,
rng=seed,
runhistory2epm=rh2EPM,
tae_runner=ta,
runhistory=runhistory)
elif self.acquisition_function == 'EIPS':
rh2EPM = RunHistory2EPM4EIPS(num_params=num_params,
scenario=self.scenario,
success_states=[
StatusType.SUCCESS,
StatusType.MEMOUT,
StatusType.TIMEOUT
],
impute_censored_data=False,
impute_state=None)
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
['cost', 'runtime'],
types,
num_trees=10,
instance_features=meta_features_list,
seed=1)
acquisition_function = EIPS(model)
_smac_arguments = dict(scenario=self.scenario,
model=model,
rng=seed,
tae_runner=ta,
runhistory2epm=rh2EPM,
runhistory=runhistory,
acquisition_function=acquisition_function)
else:
raise ValueError('Unknown acquisition function value %s!' %
self.acquisition_function)
if self.configuration_mode == 'SMAC':
smac = SMAC(**_smac_arguments)
elif self.configuration_mode in ['ROAR', 'RANDOM']:
for not_in_roar in ['runhistory2epm', 'model']:
if not_in_roar in _smac_arguments:
del _smac_arguments[not_in_roar]
smac = ROAR(**_smac_arguments)
else:
raise ValueError(self.configuration_mode)
# Build a runtime model
# runtime_rf = RandomForestWithInstances(types,
# instance_features=meta_features_list,
# seed=1, num_trees=10)
# runtime_rh2EPM = RunHistory2EPM4EIPS(num_params=num_params,
# scenario=self.scenario,
# success_states=None,
# impute_censored_data=False,
# impute_state=None)
# X_runtime, y_runtime = runtime_rh2EPM.transform(meta_runhistory)
# runtime_rf.train(X_runtime, y_runtime[:, 1].flatten())
# X_meta, Y_meta = rh2EPM.transform(meta_runhistory)
# # Transform Y_meta on a per-dataset base
# for meta_dataset in meta_runs_dataset_indices:
# start_index, end_index = meta_runs_dataset_indices[meta_dataset]
# end_index += 1 # Python indexing
# Y_meta[start_index:end_index, 0]\
# [Y_meta[start_index:end_index, 0] >2.0] = 2.0
# dataset_minimum = np.min(Y_meta[start_index:end_index, 0])
# Y_meta[start_index:end_index, 0] = 1 - (
# (1. - Y_meta[start_index:end_index, 0]) /
# (1. - dataset_minimum))
# Y_meta[start_index:end_index, 0]\
# [Y_meta[start_index:end_index, 0] > 2] = 2
smac.solver.stats.start_timing()
# == first, evaluate all metelearning and default configurations
smac.solver.incumbent = smac.solver.initial_design.run()
for challenger in metalearning_configurations:
smac.solver.incumbent, inc_perf = smac.solver.intensifier.intensify(
challengers=[challenger],
incumbent=smac.solver.incumbent,
run_history=smac.solver.runhistory,
aggregate_func=smac.solver.aggregate_func,
time_bound=self.total_walltime_limit)
if smac.solver.scenario.shared_model:
pSMAC.write(run_history=smac.solver.runhistory,
output_directory=smac.solver.scenario.output_dir,
num_run=self.seed)
if smac.solver.stats.is_budget_exhausted():
break
# == after metalearning run SMAC loop
while True:
if smac.solver.scenario.shared_model:
pSMAC.read(run_history=smac.solver.runhistory,
output_directory=self.scenario.output_dir,
configuration_space=self.config_space,
logger=self.logger)
choose_next_start_time = time.time()
try:
challengers = self.choose_next(smac)
except Exception as e:
self.logger.error(e)
self.logger.error("Error in getting next configurations "
"with SMAC. Using random configuration!")
next_config = self.config_space.sample_configuration()
challengers = [next_config]
time_for_choose_next = time.time() - choose_next_start_time
self.logger.info('Used %g seconds to find next '
'configurations' % (time_for_choose_next))
time_for_choose_next = max(time_for_choose_next, 1.0)
smac.solver.incumbent, inc_perf = smac.solver.intensifier.intensify(
challengers=challengers,
incumbent=smac.solver.incumbent,
run_history=smac.solver.runhistory,
aggregate_func=smac.solver.aggregate_func,
time_bound=time_for_choose_next)
if smac.solver.scenario.shared_model:
pSMAC.write(run_history=smac.solver.runhistory,
output_directory=smac.solver.scenario.output_dir,
num_run=self.seed)
if smac.solver.stats.is_budget_exhausted():
break
self.runhistory = smac.solver.runhistory
self.trajectory = smac.solver.intensifier.traj_logger.trajectory
return self.runhistory, self.trajectory
def build_pc_smbo(self,
tae_runner,
stats,
scenario,
runhistory,
aggregate_func,
acq_func_name,
model_target_names,
logging_directory,
double_intensification=False,
constant_pipeline_steps=None,
variable_pipeline_steps=None,
cached_pipeline_steps=None,
seed=None,
intensification_instances=None,
num_marginalized_configurations_by_random_search=20,
num_configs_for_marginalization=40,
random_splitting_number=5,
random_splitting_enabled=False):
# Build intensifier
rng = np.random.RandomState(seed)
traj_logger = TrajLogger(logging_directory, stats)
intensifier = Intensifier(tae_runner=tae_runner,
stats=stats,
traj_logger=traj_logger,
rng=rng,
cutoff=scenario.cutoff,
deterministic=scenario.deterministic,
run_obj_time=scenario.run_obj == "runtime",
run_limit=scenario.ta_run_limit,
instances=intensification_instances,
maxR=len(intensification_instances))
# Build model
types, bounds = get_types(scenario.cs, scenario.feature_array)
#types = get_types(scenario.cs)
if len(model_target_names) > 1:
# model_target_names = ['cost','time']
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
target_names=model_target_names, bounds=bounds, types=types)
# UncorrelatedMultiObjectiveRandomForestWithInstances(target_names=model_target_names,
# types=types)
elif len(model_target_names) == 1:
model = RandomForestWithInstances(types=types, bounds=bounds)
else:
model = RandomEPM(rng=rng)
# model = RandomForestWithInstances(types=types)
# Build acquisition function, runhistory2epm and local search
num_params = len(scenario.cs.get_hyperparameters())
if acq_func_name in ["ei", "pc-ei"]:
acquisition_func = EI(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name in ["m-ei", "pc-m-ei"]:
#acquisition_func = MEI(model)
acquisition_func = EI(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
# TODO: num_configs_for_marginalization
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name in ['eips', 'pc-eips']:
acquisition_func = EIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name in ["m-eips", "pc-m-eips"]:
acquisition_func = EIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
# TODO: num_configs_for_marginalization
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name == 'pceips':
acquisition_func = PCEIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapperWithCachingReduction(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
cached_pipeline_steps=cached_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
if constant_pipeline_steps == None or variable_pipeline_steps == None or cached_pipeline_steps == None:
raise ValueError(
"Constant_pipeline_steps and variable pipeline steps should not be none\
when using PCEIPS")
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name == 'pc-m-pceips':
acquisition_func = PCEIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapperWithCachingReduction(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
cached_pipeline_steps=cached_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
if constant_pipeline_steps == None or variable_pipeline_steps == None or cached_pipeline_steps == None:
raise ValueError(
"Constant_pipeline_steps and variable pipeline steps should not be none\
when using PCEIPS")
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name == "roar":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsRandom(
scenario=scenario)
elif acq_func_name == "pc-roar-mrs":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsMRS(
scenario=scenario,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
splitting_number=random_splitting_number,
random_splitting_enabled=random_splitting_enabled)
elif acq_func_name == "pc-roar-sigmoid-rs":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsSigmoidRS(
scenario=scenario,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
fraction=random_splitting_number)
else:
# Not a valid acquisition function
raise ValueError("The provided acquisition function is not valid")
# Build initial design
# initial_design = RandomConfiguration(tae_runner=tae_runner,
# scenario=scenario,
# stats=stats,
# traj_logger=traj_logger,
# rng=rng)
initial_configs = scenario.cs.sample_configuration(size=2)
for config in initial_configs:
config._populate_values()
initial_design = MultiConfigInitialDesign(
tae_runner=tae_runner,
scenario=scenario,
stats=stats,
traj_logger=traj_logger,
runhistory=runhistory,
rng=rng,
configs=initial_configs,
intensifier=intensifier,
aggregate_func=aggregate_func)
# run id
num_run = rng.randint(1234567980)
# Build pc_smbo
if acq_func_name not in ['pc-roar-sigmoid-rs']:
smbo = PCSMBO(scenario=scenario,
stats=stats,
initial_design=initial_design,
runhistory=runhistory,
runhistory2epm=runhistory2epm,
intensifier=intensifier,
aggregate_func=aggregate_func,
num_run=num_run,
model=model,
rng=rng,
select_configuration=select_configuration,
double_intensification=double_intensification)
else:
smbo = PCSMBOSigmoidRandomSearch(
scenario=scenario,
stats=stats,
initial_design=initial_design,
runhistory=runhistory,
runhistory2epm=runhistory2epm,
intensifier=intensifier,
aggregate_func=aggregate_func,
num_run=num_run,
model=model,
rng=rng,
select_configuration=select_configuration)
return smbo