def test_configure_s3_resources(self, mock_load_file, mock_create_bucket):
hook = SageMakerHook()
evaluation_result = {'Image': image, 'Role': role}
hook.configure_s3_resources(test_evaluation_config)
self.assertEqual(test_evaluation_config, evaluation_result)
mock_create_bucket.assert_called_once_with(bucket_name=bucket)
mock_load_file.assert_called_once_with(path, key, bucket)
class SageMakerBaseOperator(BaseOperator):
"""
This is the base operator for all SageMaker operators.
:param config: The configuration necessary to start a training job (templated)
:type config: dict
:param aws_conn_id: The AWS connection ID to use.
:type aws_conn_id: str
"""
template_fields = ['config']
template_ext = ()
ui_color = '#ededed'
integer_fields = [] # type: Iterable[Iterable[str]]
@apply_defaults
def __init__(self, config, aws_conn_id='aws_default', *args, **kwargs):
super().__init__(*args, **kwargs)
self.aws_conn_id = aws_conn_id
self.config = config
self.hook = None
def parse_integer(self, config, field):
"""Recursive method for parsing string fields holding integer values to integers."""
if len(field) == 1:
if isinstance(config, list):
for sub_config in config:
self.parse_integer(sub_config, field)
return
head = field[0]
if head in config:
config[head] = int(config[head])
return
if isinstance(config, list):
for sub_config in config:
self.parse_integer(sub_config, field)
return
head, tail = field[0], field[1:]
if head in config:
self.parse_integer(config[head], tail)
return
def parse_config_integers(self):
"""
Parse the integer fields of training config to integers in case the config is rendered by Jinja and
all fields are str.
"""
for field in self.integer_fields:
self.parse_integer(self.config, field)
def expand_role(self):
"""Placeholder for calling boto3's expand_role(), which expands an IAM role name into an ARN."""
def preprocess_config(self):
"""Process the config into a usable form."""
self.log.info(
'Preprocessing the config and doing required s3_operations')
self.hook = SageMakerHook(aws_conn_id=self.aws_conn_id)
self.hook.configure_s3_resources(self.config)
self.parse_config_integers()
self.expand_role()
self.log.info(
"After preprocessing the config is:\n %s",
json.dumps(self.config,
sort_keys=True,
indent=4,
separators=(",", ": ")),
)
def execute(self, context):
raise NotImplementedError('Please implement execute() in sub class!')
