def test_describe_auto_ml_job(sagemaker_session):
auto_ml = AutoML(role=ROLE,
target_attribute_name=TARGET_ATTRIBUTE_NAME,
sagemaker_session=sagemaker_session)
auto_ml.describe_auto_ml_job(job_name=JOB_NAME)
sagemaker_session.describe_auto_ml_job.assert_called_once()
sagemaker_session.describe_auto_ml_job.assert_called_with(JOB_NAME)
def test_auto_ml_describe_auto_ml_job(sagemaker_session):
expected_default_input_config = [{
"DataSource": {
"S3DataSource": {
"S3DataType":
"S3Prefix",
"S3Uri":
"s3://{}/{}/input/iris_training.csv".format(
sagemaker_session.default_bucket(), PREFIX),
}
},
"TargetAttributeName":
TARGET_ATTRIBUTE_NAME,
}]
expected_default_output_config = {
"S3OutputPath": "s3://{}/".format(sagemaker_session.default_bucket())
}
auto_ml_utils.create_auto_ml_job_if_not_exist(sagemaker_session)
auto_ml = AutoML(role=ROLE,
target_attribute_name=TARGET_ATTRIBUTE_NAME,
sagemaker_session=sagemaker_session)
desc = auto_ml.describe_auto_ml_job(job_name=AUTO_ML_JOB_NAME)
assert desc["AutoMLJobName"] == AUTO_ML_JOB_NAME
assert desc["AutoMLJobStatus"] == "Completed"
assert isinstance(desc["BestCandidate"], dict)
assert desc["InputDataConfig"] == expected_default_input_config
assert desc["AutoMLJobConfig"] == EXPECTED_DEFAULT_JOB_CONFIG
assert desc["OutputDataConfig"] == expected_default_output_config
def test_auto_ml_fit_optional_args(sagemaker_session):
output_path = "s3://{}/{}".format(sagemaker_session.default_bucket(),
"specified_ouput_path")
problem_type = "MulticlassClassification"
job_objective = {"MetricName": "Accuracy"}
auto_ml = AutoML(
role=ROLE,
target_attribute_name=TARGET_ATTRIBUTE_NAME,
sagemaker_session=sagemaker_session,
max_candidates=1,
output_path=output_path,
problem_type=problem_type,
job_objective=job_objective,
generate_candidate_definitions_only=True,
)
inputs = TRAINING_DATA
with timeout(minutes=AUTO_ML_DEFAULT_TIMEMOUT_MINUTES):
auto_ml.fit(inputs, job_name=unique_name_from_base(BASE_JOB_NAME))
auto_ml_desc = auto_ml.describe_auto_ml_job(
job_name=auto_ml.latest_auto_ml_job.job_name)
assert auto_ml_desc["AutoMLJobStatus"] == "Completed"
assert auto_ml_desc["AutoMLJobName"] == auto_ml.latest_auto_ml_job.job_name
assert auto_ml_desc["AutoMLJobObjective"] == job_objective
assert auto_ml_desc["ProblemType"] == problem_type
assert auto_ml_desc["OutputDataConfig"]["S3OutputPath"] == output_path
def test_auto_ml_describe_auto_ml_job(sagemaker_session):
auto_ml = AutoML(role=ROLE,
target_attribute_name=TARGET_ATTRIBUTE_NAME,
sagemaker_session=sagemaker_session)
desc = auto_ml.describe_auto_ml_job(job_name=AUTO_ML_JOB_NAME)
assert desc["AutoMLJobName"] == AUTO_ML_JOB_NAME
assert desc["AutoMLJobStatus"] == "Completed"
assert isinstance(desc["BestCandidate"], dict)
assert desc["InputDataConfig"] == EXPECTED_DEFAULT_INPUT_CONFIG
assert desc["AutoMLJobConfig"] == EXPECTED_DEFAULT_JOB_CONFIG
assert desc["OutputDataConfig"] == EXPECTED_DEFAULT_OUTPUT_CONFIG
def test_auto_ml_fit_optional_args(sagemaker_session):
output_path = "s3://sagemaker-us-east-2-{}/{}".format(
DEV_ACCOUNT, "specified_ouput_path")
problem_type = "MulticlassClassification"
job_objective = {"MetricName": "Accuracy"}
auto_ml = AutoML(
role=ROLE,
target_attribute_name=TARGET_ATTRIBUTE_NAME,
sagemaker_session=sagemaker_session,
max_candidates=1,
output_path=output_path,
problem_type=problem_type,
job_objective=job_objective,
)
inputs = TRAINING_DATA
with timeout(minutes=AUTO_ML_DEFAULT_TIMEMOUT_MINUTES):
auto_ml.fit(inputs, job_name=JOB_NAME)
auto_ml_desc = auto_ml.describe_auto_ml_job(job_name=JOB_NAME)
assert auto_ml_desc["AutoMLJobStatus"] == "Completed"
assert auto_ml_desc["AutoMLJobName"] == JOB_NAME
assert auto_ml_desc["AutoMLJobObjective"] == job_objective
assert auto_ml_desc["ProblemType"] == problem_type
assert auto_ml_desc["OutputDataConfig"]["S3OutputPath"] == output_path
