def test_cls():
save_dir = './data/eval_exps/soln-ml'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
time_limit = 60
print('==> Start to evaluate with Budget %d' % time_limit)
ensemble_method = 'ensemble_selection'
eval_type = 'holdout'
iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=1, stratify=y)
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)
clf = Classifier(time_limit=time_limit,
output_dir=save_dir,
ensemble_method=ensemble_method,
enable_meta_algorithm_selection=True,
ensemble_size=10,
evaluation=eval_type,
metric='bal_acc')
clf.fit(train_data)
print(clf.summary())
pred = clf.predict(test_data)
print(accuracy_score(test_data.data[1], pred))
shutil.rmtree(save_dir)
def main():
tmp_dir = './data/eval_exps/soln-ml'
if not os.path.exists(tmp_dir):
os.makedirs(tmp_dir)
time_limit = 60
print('==> Start new AutoML task with budget - %d' % time_limit)
ensemble_method = 'ensemble_selection'
eval_type = 'holdout'
iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=1,
stratify=y)
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)
clf = Classifier(time_limit=time_limit,
output_dir=tmp_dir,
ensemble_method=ensemble_method,
enable_meta_algorithm_selection=False,
ensemble_size=10,
optimizer='random_search',
evaluation=eval_type,
metric='acc',
n_jobs=1)
clf.fit(train_data, tree_id=2)
print(clf.summary())
pred = clf.predict(test_data)
print(accuracy_score(test_data.data[1], pred))
shutil.rmtree(tmp_dir)
eval_type = args.eval_type
n_jobs = args.n_jobs
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)