def test_rgs():
time_limit = 120
print('==> Start to evaluate with Budget %d' % time_limit)
ensemble_method = 'blending'
eval_type = 'holdout'
boston = load_boston()
X, y = boston.data, boston.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=1)
dm = DataManager(X_train, y_train)
train_data = dm.get_data_node(X_train, y_train)
test_data = dm.get_data_node(X_test, y_test)
save_dir = './data/eval_exps/soln-ml'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
rgs = Regressor(metric='mse',
ensemble_method=ensemble_method,
evaluation=eval_type,
time_limit=time_limit,
output_dir=save_dir)
rgs.fit(train_data)
pred = rgs.predict(test_data)
print(mean_squared_error(test_data.data[1], pred))
def evaluate_sys(run_id, task_type, mth, dataset, ens_method, enable_meta,
eval_type='holdout', time_limit=1200, seed=1):
_task_type = MULTICLASS_CLS if task_type == 'cls' else REGRESSION
train_data, test_data = load_train_test_data(dataset, task_type=_task_type)
_enable_meta = True if enable_meta == 'true' else False
if task_type == 'cls':
from solnml.estimators import Classifier
estimator = Classifier(time_limit=time_limit,
per_run_time_limit=300,
output_dir=save_folder,
ensemble_method=ens_method,
enable_meta_algorithm_selection=_enable_meta,
evaluation=eval_type,
metric='bal_acc',
include_algorithms=['random_forest'],
include_preprocessors=['extra_trees_based_selector',
'generic_univariate_selector',
'liblinear_based_selector',
'percentile_selector'],
n_jobs=1)
else:
from solnml.estimators import Regressor
estimator = Regressor(time_limit=time_limit,
per_run_time_limit=300,
output_dir=save_folder,
ensemble_method=ens_method,
enable_meta_algorithm_selection=_enable_meta,
evaluation=eval_type,
metric='mse',
include_algorithms=['random_forest'],
include_preprocessors=['extra_trees_based_selector_regression',
'generic_univariate_selector',
'liblinear_based_selector',
'percentile_selector_regression'],
n_jobs=1)
start_time = time.time()
estimator.fit(train_data, opt_strategy=mth, dataset_id=dataset)
pred = estimator.predict(test_data)
if task_type == 'cls':
test_score = balanced_accuracy_score(test_data.data[1], pred)
else:
test_score = mean_squared_error(test_data.data[1], pred)
validation_score = estimator._ml_engine.solver.incumbent_perf
eval_dict = estimator._ml_engine.solver.get_eval_dict()
print('Run ID : %d' % run_id)
print('Dataset : %s' % dataset)
print('Val/Test score : %f - %f' % (validation_score, test_score))
save_path = save_folder + 'extremely_small_%s_%s_%s_%s_%d_%d_%d.pkl' % (
task_type, mth, dataset, enable_meta, time_limit, (ens_method is None), run_id)
with open(save_path, 'wb') as f:
pickle.dump([dataset, validation_score, test_score, start_time, eval_dict], f)
# Delete output dir
shutil.rmtree(os.path.join(estimator.get_output_dir()))
def model_fit(_id,obj,paramsj,X_trainj,y_trainj):
info_path = './models_information/'+_id+'_information'
info_file = open(info_path,'w')
print('Model training begins!')
try:
# read data
X_train = np.array(pd.DataFrame(json.loads(X_trainj)))
y_train = np.array(pd.DataFrame(json.loads(y_trainj)))[:,0]
params = json.loads(paramsj)
#print(y_train)
dm = DataManager(X_train, y_train)
train_data = dm.get_data_node(X_train, y_train)
save_dir = '../data/eval_exps/soln-ml'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
# train mode
if(obj == 'clf'):
mdl = Classifier(time_limit=params['time_limit'],
output_dir=save_dir,
ensemble_method=params['ensemble_method'],
evaluation=params['evaluation'],
metric=params['metric'],
n_jobs=4)
elif(obj == 'reg'):
mdl = rgs = Regressor(metric=params['metric'],
ensemble_method=params['ensemble_method'],
evaluation=params['evaluation'],
time_limit=params['time_limit'],
output_dir=save_dir,
random_state=1,
n_jobs=n_jobs)
mdl.fit(train_data)
except:
print('Model training failed!')
info_file.write('Model training failed!')
info_file.close()
return -1
result = dict()
result['best_algo_id'] = str(mdl.best_algo_id)
result['best_hpo_config'] = str(mdl.best_hpo_config)
result['nbest_algo_id'] = str(mdl.nbest_algo_id)
result['best_perf'] = str(mdl.best_perf)
result['best_fe_config'] = str(mdl.best_fe_config)
result['get_ens_model_info'] = str(mdl.get_ens_model_info)
#get_ens_model_info is not realized in this version yet
info_file.write(json.dumps(result))
info_file.close()
print('Model training finished!')
return 0
ensemble_method = args.ens_method
if ensemble_method == 'none':
ensemble_method = None
print('==> Start to evaluate with Budget %d' % time_limit)
boston = load_boston()
X, y = boston.data, boston.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=1)
dm = DataManager(X_train, y_train)
train_data = dm.get_data_node(X_train, y_train)
test_data = dm.get_data_node(X_test, y_test)
save_dir = './data/eval_exps/soln-ml'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
rgs = Regressor(metric='mse',
dataset_name='boston',
ensemble_method=ensemble_method,
evaluation=eval_type,
time_limit=time_limit,
output_dir=save_dir,
random_state=1,
n_jobs=n_jobs)
rgs.fit(train_data)
pred = rgs.predict(test_data)
print(mean_squared_error(test_data.data[1], pred))
