def main(args):
print("args.local=", args.local)
# Initialise SDK
sklearn_estimator = SKLearn(
entry_point='src/train_and_deploy.py',
role=CLOUD_CONFIG['sagemaker_role_id']['value'],
train_instance_type='local' if args.local else 'ml.m4.xlarge',
hyperparameters={
'sagemaker_submit_directory':
f"s3://{CLOUD_CONFIG['s3bucket']['value']}",
},
framework_version='0.23-1',
metric_definitions=[{
'Name': 'train:score',
'Regex': 'train:score=(\S+)'
}],
)
# Run model training job
sklearn_estimator.fit({
'train':
"file://./data/data.csv"
if args.local else f"s3://{CLOUD_CONFIG['s3bucket']['value']}/data.csv"
})
# Deploy trained model to an endpoint
sklearn_estimator.deploy(
instance_type='local' if args.local else 'ml.t2.medium',
initial_instance_count=1,
endpoint_name='demo-endpoint',
)
def main():
print('Starting model training.')
print('Note: if launching for the first time in local mode, container image download might take a few minutes to complete.')
sklearn = SKLearn(
entry_point="scikit_boston_housing.py",
source_dir='code',
framework_version="0.23-1",
instance_type="local",
role=DUMMY_IAM_ROLE
)
delta_lake_profile_file = "file://./profile/open-datasets.share"
sklearn.fit({"train": delta_lake_profile_file})
print('Completed model training')
print('Deploying endpoint in local mode')
predictor = sklearn.deploy(initial_instance_count=1, instance_type='local')
test_sample = [[0.00632,18.0,2.31,0,0.538,6.575,65.2,4.0900,1,296,15.3,396.90,4.98]]
prediction = predictor.predict(test_sample)
print(f'Prediction: {prediction}')
print('About to delete the endpoint to stop paying (if in cloud mode).')
predictor.delete_endpoint(predictor.endpoint_name)
def main():
download_training_and_eval_data()
print('Starting model training.')
print(
'Note: if launching for the first time in local mode, container image download might take a few minutes to complete.'
)
sklearn = SKLearn(
entry_point="scikit_learn_iris.py",
source_dir='code',
framework_version="0.23-1",
instance_type="local",
role=DUMMY_IAM_ROLE,
hyperparameters={"max_leaf_nodes": 30},
)
train_input = "file://./data/iris.csv"
sklearn.fit({"train": train_input})
print('Completed model training')
print('Deploying endpoint in local mode')
predictor = sklearn.deploy(initial_instance_count=1, instance_type='local')
do_inference_on_local_endpoint(predictor)
print('About to delete the endpoint to stop paying (if in cloud mode).')
predictor.delete_endpoint(predictor.endpoint_name)
def main():
download_training_and_eval_data()
print('Starting model training.')
print(
'Note: if launching for the first time in local mode, container image download might take a few minutes to complete.'
)
sklearn = SKLearn(
entry_point="catboost_train_deploy.py",
source_dir='code',
framework_version="0.23-1",
instance_type="local",
role=DUMMY_IAM_ROLE,
)
train_location = 'file://' + local_train
validation_location = 'file://' + local_validation
sklearn.fit({'train': train_location, 'validation': validation_location})
print('Completed model training')
print('Deploying endpoint in local mode')
predictor = sklearn.deploy(1, 'local', serializer=csv_serializer)
with open(local_test, 'r') as f:
payload = f.read().strip()
predictions = predictor.predict(payload)
print('predictions: {}'.format(predictions))
predictor.delete_endpoint(predictor.endpoint)
def test_sklearn(strftime, sagemaker_session, sklearn_version):
sklearn = SKLearn(
entry_point=SCRIPT_PATH,
role=ROLE,
sagemaker_session=sagemaker_session,
train_instance_type=INSTANCE_TYPE,
py_version=PYTHON_VERSION,
framework_version=sklearn_version,
)
inputs = "s3://mybucket/train"
sklearn.fit(inputs=inputs, experiment_config=EXPERIMENT_CONFIG)
sagemaker_call_names = [c[0] for c in sagemaker_session.method_calls]
assert sagemaker_call_names == ["train", "logs_for_job"]
boto_call_names = [
c[0] for c in sagemaker_session.boto_session.method_calls
]
assert boto_call_names == ["resource"]
expected_train_args = _create_train_job(sklearn_version)
expected_train_args["input_config"][0]["DataSource"]["S3DataSource"][
"S3Uri"] = inputs
expected_train_args["experiment_config"] = EXPERIMENT_CONFIG
actual_train_args = sagemaker_session.method_calls[0][2]
assert actual_train_args == expected_train_args
model = sklearn.create_model()
expected_image_base = (
"246618743249.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:{}-cpu-{}"
)
assert {
"Environment": {
"SAGEMAKER_SUBMIT_DIRECTORY":
"s3://mybucket/sagemaker-scikit-learn-{}/source/sourcedir.tar.gz".
format(TIMESTAMP),
"SAGEMAKER_PROGRAM":
"dummy_script.py",
"SAGEMAKER_ENABLE_CLOUDWATCH_METRICS":
"false",
"SAGEMAKER_REGION":
"us-west-2",
"SAGEMAKER_CONTAINER_LOG_LEVEL":
"20",
},
"Image": expected_image_base.format(sklearn_version, PYTHON_VERSION),
"ModelDataUrl": "s3://m/m.tar.gz",
} == model.prepare_container_def(CPU)
assert "cpu" in model.prepare_container_def(CPU)["Image"]
predictor = sklearn.deploy(1, CPU)
assert isinstance(predictor, SKLearnPredictor)
def test_sklearn(strftime, sagemaker_session, sklearn_version):
sklearn = SKLearn(entry_point=SCRIPT_PATH,
role=ROLE,
sagemaker_session=sagemaker_session,
train_instance_type=INSTANCE_TYPE,
py_version=PYTHON_VERSION,
framework_version=sklearn_version)
inputs = 's3://mybucket/train'
sklearn.fit(inputs=inputs)
sagemaker_call_names = [c[0] for c in sagemaker_session.method_calls]
assert sagemaker_call_names == ['train', 'logs_for_job']
boto_call_names = [
c[0] for c in sagemaker_session.boto_session.method_calls
]
assert boto_call_names == ['resource']
expected_train_args = _create_train_job(sklearn_version)
expected_train_args['input_config'][0]['DataSource']['S3DataSource'][
'S3Uri'] = inputs
actual_train_args = sagemaker_session.method_calls[0][2]
assert actual_train_args == expected_train_args
model = sklearn.create_model()
expected_image_base = '246618743249.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:{}-cpu-{}'
assert {
'Environment': {
'SAGEMAKER_SUBMIT_DIRECTORY':
's3://mybucket/sagemaker-scikit-learn-{}/source/sourcedir.tar.gz'.
format(TIMESTAMP),
'SAGEMAKER_PROGRAM':
'dummy_script.py',
'SAGEMAKER_ENABLE_CLOUDWATCH_METRICS':
'false',
'SAGEMAKER_REGION':
'us-west-2',
'SAGEMAKER_CONTAINER_LOG_LEVEL':
'20'
},
'Image': expected_image_base.format(sklearn_version, PYTHON_VERSION),
'ModelDataUrl': 's3://m/m.tar.gz'
} == model.prepare_container_def(CPU)
assert 'cpu' in model.prepare_container_def(CPU)['Image']
predictor = sklearn.deploy(1, CPU)
assert isinstance(predictor, SKLearnPredictor)
from sagemaker.sklearn import SKLearn
# Initialise SDK
sklearn_estimator = SKLearn(
entry_point='train_and_deploy.py',
role='arn:aws:iam::<your-sagemaker-role>',
# train_instance_type='ml.m4.xlarge',
train_instance_type='local',
output_path='s3://<path-to-output-dir>/',
hyperparameters={
'sagemaker_submit_directory':
's3://<path-to-sagemaker_submit_directory>'
},
code_location='s3://<path-to-code_location>',
framework_version='0.20.0')
# Run model training job
sklearn_estimator.fit({'train': 's3://<path-to-training-data-dir>'})
# Deploy trained model to an endpoint
predictor = sklearn_estimator.deploy(
# instance_type='ml.t2.medium',
instance_type='local',
initial_instance_count=1,
endpoint_name='<your-end-point-name>',
)
