Skip to content

Add integration tests for basic training failure cases #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jan 9, 2018
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions tests/data/iris/failure_script.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
def estimator_fn(run_config, params):
"""For use with integration tests expecting failures."""
raise Exception('This failure is expected.')
3 changes: 3 additions & 0 deletions tests/data/mxnet_mnist/failure_script.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
def train(**kwargs):
"""For use with integration tests expecting failures."""
raise Exception('This failure is expected.')
17 changes: 17 additions & 0 deletions tests/integ/test_mxnet_train.py
Original file line number Diff line number Diff line change
Expand Up @@ -70,3 +70,20 @@ def test_deploy_model(mxnet_training_job, sagemaker_session):

data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)


def test_failed_training_job(sagemaker_session):
with timeout(minutes=15):
script_path = os.path.join(DATA_DIR, 'mxnet_mnist', 'failure_script.py')
data_path = os.path.join(DATA_DIR, 'mxnet_mnist')

mx = MXNet(entry_point=script_path, role='SageMakerRole',
train_instance_count=1, train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session)

train_input = mx.sagemaker_session.upload_data(path=os.path.join(data_path, 'train'),
key_prefix='integ-test-data/mxnet_mnist/train-failure')

with pytest.raises(ValueError) as e:
mx.fit(train_input)
assert 'This failure is expected' in str(e.value)
24 changes: 22 additions & 2 deletions tests/integ/test_tf.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@
from tests.integ import DATA_DIR, REGION
from tests.integ.timeout import timeout_and_delete_endpoint, timeout

DATA_PATH = os.path.join(DATA_DIR, 'iris', 'data')


@pytest.fixture(scope='module')
def sagemaker_session():
Expand All @@ -28,7 +30,6 @@ def sagemaker_session():
def test_tf(sagemaker_session):
with timeout(minutes=15):
script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')
data_path = os.path.join(DATA_DIR, 'iris', 'data')

estimator = TensorFlow(entry_point=script_path,
role='SageMakerRole',
Expand All @@ -40,7 +41,7 @@ def test_tf(sagemaker_session):
sagemaker_session=sagemaker_session,
base_job_name='test-tf')

inputs = estimator.sagemaker_session.upload_data(path=data_path, key_prefix='integ-test-data/tf_iris')
inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf_iris')
estimator.fit(inputs)
print('job succeeded: {}'.format(estimator.latest_training_job.name))

Expand All @@ -49,3 +50,22 @@ def test_tf(sagemaker_session):

result = json_predictor.predict([6.4, 3.2, 4.5, 1.5])
print('predict result: {}'.format(result))


def test_failed_tf_training(sagemaker_session):
with timeout(minutes=15):
script_path = os.path.join(DATA_DIR, 'iris', 'failure_script.py')
estimator = TensorFlow(entry_point=script_path,
role='SageMakerRole',
training_steps=1,
evaluation_steps=1,
hyperparameters={'input_tensor_name': 'inputs'},
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session)

inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf-failure')

with pytest.raises(ValueError) as e:
estimator.fit(inputs)
assert 'This failure is expected' in str(e.value)