def test_algorithm_required_hyperparameters_not_provided(session):
hyperparameters = [
{
"Description": "A continuous hyperparameter",
"Type": "Categorical",
"Name": "hp1",
"Range": {
"CategoricalParameterRangeSpecification": {
"Values": ["TF", "MXNet"]
}
},
"IsTunable": True,
"IsRequired": True,
},
{
"Name": "hp2",
"Description": "A continuous hyperparameter",
"Type": "Categorical",
"IsTunable": False,
"IsRequired": True,
},
]
some_algo = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
some_algo["TrainingSpecification"][
"SupportedHyperParameters"] = hyperparameters
session.sagemaker_client.describe_algorithm = Mock(return_value=some_algo)
estimator = AlgorithmEstimator(
algorithm_arn=
"arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees",
role="SageMakerRole",
train_instance_type="ml.m4.2xlarge",
train_instance_count=1,
sagemaker_session=session,
)
# hp1 is required and was not provided
with pytest.raises(ValueError):
estimator.set_hyperparameters(hp2="TF2")
# Calling fit with unset required hyperparameters should fail
# this covers the use case of not calling set_hyperparameters() explicitly
with pytest.raises(ValueError):
estimator.fit({"training": "s3://some/place"})
def test_algorithm_trainining_channels_with_invalid_channels(
sagemaker_session):
training_channels = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
training_channels['TrainingSpecification']['TrainingChannels'] = [
{
'Name': 'training',
'Description': 'Input channel that provides training data',
'IsRequired': True,
'SupportedContentTypes': ['text/csv'],
'SupportedCompressionTypes': ['None'],
'SupportedInputModes': ['File'],
},
{
'Name': 'validation',
'Description': 'Input channel that provides validation data',
'IsRequired': False,
'SupportedContentTypes': ['text/csv'],
'SupportedCompressionTypes': ['None'],
'SupportedInputModes': ['File'],
},
]
sagemaker_session.sagemaker_client.describe_algorithm = Mock(
return_value=training_channels)
estimator = AlgorithmEstimator(
algorithm_arn=
'arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees',
role='SageMakerRole',
train_instance_type='ml.m4.xlarge',
train_instance_count=1,
sagemaker_session=sagemaker_session,
)
# Passing only validation should fail as training is required.
with pytest.raises(ValueError):
estimator.fit({'validation': 's3://some/thing'})
# Passing an unknown channel should fail???
with pytest.raises(ValueError):
estimator.fit({
'training': 's3://some/data',
'training2': 's3://some/other/data'
})
def test_algorithm_trainining_channels_with_invalid_channels(session):
training_channels = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
training_channels["TrainingSpecification"]["TrainingChannels"] = [
{
"Name": "training",
"Description": "Input channel that provides training data",
"IsRequired": True,
"SupportedContentTypes": ["text/csv"],
"SupportedCompressionTypes": ["None"],
"SupportedInputModes": ["File"],
},
{
"Name": "validation",
"Description": "Input channel that provides validation data",
"IsRequired": False,
"SupportedContentTypes": ["text/csv"],
"SupportedCompressionTypes": ["None"],
"SupportedInputModes": ["File"],
},
]
session.sagemaker_client.describe_algorithm = Mock(
return_value=training_channels)
estimator = AlgorithmEstimator(
algorithm_arn=
"arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees",
role="SageMakerRole",
train_instance_type="ml.m4.xlarge",
train_instance_count=1,
sagemaker_session=session,
)
# Passing only validation should fail as training is required.
with pytest.raises(ValueError):
estimator.fit({"validation": "s3://some/thing"})
# Passing an unknown channel should fail???
with pytest.raises(ValueError):
estimator.fit({
"training": "s3://some/data",
"training2": "s3://some/other/data"
})
def test_algorithm_required_hyperparameters_not_provided(sagemaker_session):
hyperparameters = [{
'Description': 'A continuous hyperparameter',
'Type': 'Categorical',
'Name': 'hp1',
'Range': {
'CategoricalParameterRangeSpecification': {
'Values': ['TF', 'MXNet']
}
},
'IsTunable': True,
'IsRequired': True,
}, {
'Name': 'hp2',
'Description': 'A continuous hyperparameter',
'Type': 'Categorical',
'IsTunable': False,
'IsRequired': True
}]
some_algo = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
some_algo['TrainingSpecification'][
'SupportedHyperParameters'] = hyperparameters
sagemaker_session.sagemaker_client.describe_algorithm = Mock(
return_value=some_algo)
estimator = AlgorithmEstimator(
algorithm_arn=
'arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees',
role='SageMakerRole',
train_instance_type='ml.m4.2xlarge',
train_instance_count=1,
sagemaker_session=sagemaker_session,
)
# hp1 is required and was not provided
with pytest.raises(ValueError):
estimator.set_hyperparameters(hp2='TF2')
# Calling fit with unset required hyperparameters should fail
# this covers the use case of not calling set_hyperparameters() explicitly
with pytest.raises(ValueError):
estimator.fit({'training': 's3://some/place'})
def test_algorithm_trainining_channels_with_expected_channels(
sagemaker_session):
training_channels = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
training_channels['TrainingSpecification']['TrainingChannels'] = [
{
'Name': 'training',
'Description': 'Input channel that provides training data',
'IsRequired': True,
'SupportedContentTypes': ['text/csv'],
'SupportedCompressionTypes': ['None'],
'SupportedInputModes': ['File'],
},
{
'Name': 'validation',
'Description': 'Input channel that provides validation data',
'IsRequired': False,
'SupportedContentTypes': ['text/csv'],
'SupportedCompressionTypes': ['None'],
'SupportedInputModes': ['File'],
},
]
sagemaker_session.sagemaker_client.describe_algorithm = Mock(
return_value=training_channels)
estimator = AlgorithmEstimator(
algorithm_arn=
'arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees',
role='SageMakerRole',
train_instance_type='ml.m4.xlarge',
train_instance_count=1,
sagemaker_session=sagemaker_session,
)
# Pass training and validation channels. This should work
estimator.fit({
'training': 's3://some/place',
'validation': 's3://some/other'
})
# Passing only the training channel. Validation is optional so this should also work.
estimator.fit({'training': 's3://some/place'})
def test_algorithm_trainining_channels_with_expected_channels(session):
training_channels = copy.deepcopy(DESCRIBE_ALGORITHM_RESPONSE)
training_channels["TrainingSpecification"]["TrainingChannels"] = [
{
"Name": "training",
"Description": "Input channel that provides training data",
"IsRequired": True,
"SupportedContentTypes": ["text/csv"],
"SupportedCompressionTypes": ["None"],
"SupportedInputModes": ["File"],
},
{
"Name": "validation",
"Description": "Input channel that provides validation data",
"IsRequired": False,
"SupportedContentTypes": ["text/csv"],
"SupportedCompressionTypes": ["None"],
"SupportedInputModes": ["File"],
},
]
session.sagemaker_client.describe_algorithm = Mock(
return_value=training_channels)
estimator = AlgorithmEstimator(
algorithm_arn=
"arn:aws:sagemaker:us-east-2:1234:algorithm/scikit-decision-trees",
role="SageMakerRole",
train_instance_type="ml.m4.xlarge",
train_instance_count=1,
sagemaker_session=session,
)
# Pass training and validation channels. This should work
estimator.fit({
"training": "s3://some/place",
"validation": "s3://some/other"
})
# Passing only the training channel. Validation is optional so this should also work.
estimator.fit({"training": "s3://some/place"})
