def __init__(self, state_id, transformer, job_name, model_name, data, data_type='S3Prefix', content_type=None, compression_type=None, split_type=None, wait_for_completion=True, **kwargs):
"""
Args:
state_id (str): State name whose length **must be** less than or equal to 128 unicode characters. State names **must be** unique within the scope of the whole state machine.
transformer (sagemaker.transformer.Transformer): The SageMaker transformer to use in the TransformStep.
job_name (str or Placeholder): Specify a transform job name. We recommend to use :py:class:`~stepfunctions.inputs.ExecutionInput` placeholder collection to pass the value dynamically in each execution.
model_name (str or Placeholder): Specify a model name for the transform job to use. We recommend to use :py:class:`~stepfunctions.inputs.ExecutionInput` placeholder collection to pass the value dynamically in each execution.
data (str): Input data location in S3.
data_type (str): What the S3 location defines (default: 'S3Prefix').
Valid values:
* 'S3Prefix' - the S3 URI defines a key name prefix. All objects with this prefix will
be used as inputs for the transform job.
* 'ManifestFile' - the S3 URI points to a single manifest file listing each S3 object
to use as an input for the transform job.
content_type (str): MIME type of the input data (default: None).
compression_type (str): Compression type of the input data, if compressed (default: None). Valid values: 'Gzip', None.
split_type (str): The record delimiter for the input object (default: 'None'). Valid values: 'None', 'Line', 'RecordIO', and 'TFRecord'.
wait_for_completion(bool, optional): Boolean value set to `True` if the Task state should wait for the transform job to complete before proceeding to the next step in the workflow. Set to `False` if the Task state should submit the transform job and proceed to the next step. (default: True)
"""
if wait_for_completion:
kwargs[Field.Resource.value] = 'arn:aws:states:::sagemaker:createTransformJob.sync'
else:
kwargs[Field.Resource.value] = 'arn:aws:states:::sagemaker:createTransformJob'
if isinstance(job_name, str):
parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type,
job_name=job_name
)
else:
parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type
)
if isinstance(job_name, (ExecutionInput, StepInput)):
parameters['TransformJobName'] = job_name
parameters['ModelName'] = model_name
kwargs[Field.Parameters.value] = parameters
super(TransformStep, self).__init__(state_id, **kwargs)
def test_transform_config(sagemaker_session):
tf_transformer = transformer.Transformer(
model_name="tensorflow-model",
instance_count="{{ instance_count }}",
instance_type="ml.p2.xlarge",
strategy="SingleRecord",
assemble_with='Line',
output_path="{{ output_path }}",
output_kms_key="{{ kms_key }}",
accept="{{ accept }}",
max_concurrent_transforms="{{ max_parallel_job }}",
max_payload="{{ max_payload }}",
tags=[{"{{ key }}": "{{ value }}"}],
env={"{{ key }}": "{{ value }}"},
base_transform_job_name="tensorflow-transform",
sagemaker_session=sagemaker_session,
volume_kms_key="{{ kms_key }}")
data = "{{ transform_data }}"
config = airflow.transform_config(tf_transformer, data, data_type='S3Prefix', content_type="{{ content_type }}",
compression_type="{{ compression_type }}", split_type="{{ split_type }}")
expected_config = {
'TransformJobName': "tensorflow-transform-%s" % TIME_STAMP,
'ModelName': 'tensorflow-model',
'TransformInput': {
'DataSource': {
'S3DataSource': {
'S3DataType': 'S3Prefix',
'S3Uri': '{{ transform_data }}'
}
},
'ContentType': '{{ content_type }}',
'CompressionType': '{{ compression_type }}',
'SplitType': '{{ split_type }}'},
'TransformOutput': {
'S3OutputPath': '{{ output_path }}',
'KmsKeyId': '{{ kms_key }}',
'AssembleWith': 'Line',
'Accept': '{{ accept }}'
},
'TransformResources': {
'InstanceCount': '{{ instance_count }}',
'InstanceType': 'ml.p2.xlarge',
'VolumeKmsKeyId': '{{ kms_key }}'
},
'BatchStrategy': 'SingleRecord',
'MaxConcurrentTransforms': '{{ max_parallel_job }}',
'MaxPayloadInMB': '{{ max_payload }}',
'Environment': {'{{ key }}': '{{ value }}'},
'Tags': [{'{{ key }}': '{{ value }}'}]
}
assert config == expected_config
def __init__(
self,
state_id,
transformer,
job_name,
model_name,
data,
outputpath,
data_type="S3Prefix",
content_type=None,
compression_type=None,
split_type=None,
experiment_config=None,
wait_for_completion=True,
tags=None,
input_filter=None,
output_filter=None,
join_source=None,
**kwargs,
):
"""
Args:
state_id (str): State name whose length **must be** less than or
equal to 128 unicode characters. State names **must be** unique
within the scope of the whole state machine.
transformer (sagemaker.transformer.Transformer): The SageMaker
transformer to use in the TransformStep.
job_name (str or Placeholder): Specify a transform job name. We
recommend to use :py:class:`~stepfunctions.inputs.ExecutionInput`
placeholder collection to pass the value dynamically in each
execution.
model_name (str or Placeholder): Specify a model name for the
transform job to use. We recommend to use
:py:class:`~stepfunctions.inputs.ExecutionInput` placeholder
collection to pass the value dynamically in each execution.
data (str): Input data location in S3.
data_type (str): What the S3 location defines (default: 'S3Prefix').
Valid values:
* 'S3Prefix' - the S3 URI defines a key name prefix. All
objects with this prefix will be used as inputs for the
transform job.
* 'ManifestFile' - the S3 URI points to a single manifest file
listing each S3 object
to use as an input for the transform job.
content_type (str): MIME type of the input data (default: None).
compression_type (str): Compression type of the input data, if
compressed (default: None). Valid values: 'Gzip', None.
split_type (str): The record delimiter for the input object
(default: 'None'). Valid values: 'None', 'Line', 'RecordIO', and
'TFRecord'.
experiment_config (dict, optional): Specify the experiment config
for the transform. (Default: None)
wait_for_completion(bool, optional): Boolean value set to `True` if
the Task state should wait for the transform job to complete before
proceeding to the next step in the workflow. Set to `False` if the
Task state should submit the transform job and proceed to the next
step. (default: True)
tags (list[dict], optional): `List to tags
<https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html>`_ to
associate with the resource.
input_filter (str): A JSONPath to select a portion of the input to
pass to the algorithm container for inference. If you omit the
field, it gets the value ‘$’, representing the entire input. For
CSV data, each row is taken as a JSON array, so only index-based
JSONPaths can be applied, e.g. $[0], $[1:]. CSV data should follow
the RFC format. See Supported JSONPath Operators for a table of
supported JSONPath operators. For more information, see the
SageMaker API documentation for CreateTransformJob. Some examples:
“$[1:]”, “$.features” (default: None).
output_filter (str): A JSONPath to select a portion of the
joined/original output to return as the output. For more
information, see the SageMaker API documentation for
CreateTransformJob. Some examples: “$[1:]”, “$.prediction”
(default: None).
join_source (str): The source of data to be joined to the transform
output. It can be set to ‘Input’ meaning the entire input record
will be joined to the inference result. You can use OutputFilter to
select the useful portion before uploading to S3. (default: None).
Valid values: Input, None.
"""
if wait_for_completion:
kwargs[
Field.Resource.value
] = "arn:aws:states:::sagemaker:createTransformJob.sync"
else:
kwargs[
Field.Resource.value
] = "arn:aws:states:::sagemaker:createTransformJob"
if isinstance(job_name, str):
parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type,
job_name=job_name,
input_filter=input_filter,
output_filter=output_filter,
join_source=join_source,
)
else:
parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type,
input_filter=input_filter,
output_filter=output_filter,
join_source=join_source,
)
if isinstance(job_name, (ExecutionInput, StepInput)):
parameters["TransformJobName"] = job_name
parameters["ModelName"] = model_name
parameters["TransformOutput"]["S3OutputPath"] = outputpath
if experiment_config is not None:
parameters["ExperimentConfig"] = experiment_config
if tags:
parameters["Tags"] = tags_dict_to_kv_list(tags)
# print(parameters)
kwargs[Field.Parameters.value] = parameters
super(MLMaxBatchTransformStep, self).__init__(state_id, **kwargs)
# train_config specifies SageMaker training configuration
train_data = create_s3_input(config['train_model']['inputs']['train'])
validation_data = create_s3_input(
config['train_model']['inputs']['validation'])
data_channels = {'train': train_data, 'validation': validation_data}
train_config = training_config(estimator=xgb_estimator, inputs=data_channels)
# Batch inference
xgb_transformer = Transformer(
model_name=config['batch_transform']['model_name'],
sagemaker_session=sagemaker.session.Session(sess),
**config['batch_transform']['transformer_config'])
transform_config = transform_config(
transformer=xgb_transformer,
**config['batch_transform']['transform_config'])
# =============================================================================
# define airflow DAG and tasks
# =============================================================================
# define airflow DAG
args = {'owner': 'airflow', 'start_date': airflow.utils.dates.days_ago(2)}
dag = DAG(
'sagemaker-ml-pipeline',
default_args=args,
schedule_interval=None,
concurrency=1,
max_active_runs=1,
user_defined_filters={'tojson': lambda s: json.JSONEncoder().encode(s)})
def __init__(self,
state_id,
transformer,
job_name,
model_name,
data,
data_type='S3Prefix',
content_type=None,
compression_type=None,
split_type=None,
experiment_config=None,
wait_for_completion=True,
tags=None,
input_filter=None,
output_filter=None,
join_source=None,
**kwargs):
"""
Args:
state_id (str): State name whose length **must be** less than or equal to 128 unicode characters. State names **must be** unique within the scope of the whole state machine.
transformer (sagemaker.transformer.Transformer): The SageMaker transformer to use in the TransformStep.
job_name (str or Placeholder): Specify a transform job name. We recommend to use :py:class:`~stepfunctions.inputs.ExecutionInput` placeholder collection to pass the value dynamically in each execution.
model_name (str or Placeholder): Specify a model name for the transform job to use. We recommend to use :py:class:`~stepfunctions.inputs.ExecutionInput` placeholder collection to pass the value dynamically in each execution.
data (str or Placeholder): Input data location in S3.
data_type (str or Placeholder): What the S3 location defines (default: 'S3Prefix').
Valid values:
* 'S3Prefix' - the S3 URI defines a key name prefix. All objects with this prefix will
be used as inputs for the transform job.
* 'ManifestFile' - the S3 URI points to a single manifest file listing each S3 object
to use as an input for the transform job.
content_type (str or Placeholder): MIME type of the input data (default: None).
compression_type (str or Placeholder): Compression type of the input data, if compressed (default: None). Valid values: 'Gzip', None.
split_type (str or Placeholder): The record delimiter for the input object (default: 'None'). Valid values: 'None', 'Line', 'RecordIO', and 'TFRecord'.
experiment_config (dict or Placeholder, optional): Specify the experiment config for the transform. (Default: None)
wait_for_completion(bool, optional): Boolean value set to `True` if the Task state should wait for the transform job to complete before proceeding to the next step in the workflow. Set to `False` if the Task state should submit the transform job and proceed to the next step. (default: True)
tags (list[dict] or Placeholder, optional): `List to tags <https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html>`_ to associate with the resource.
input_filter (str or Placeholder): A JSONPath to select a portion of the input to pass to the algorithm container for inference. If you omit the field, it gets the value ‘$’, representing the entire input. For CSV data, each row is taken as a JSON array, so only index-based JSONPaths can be applied, e.g. $[0], $[1:]. CSV data should follow the RFC format. See Supported JSONPath Operators for a table of supported JSONPath operators. For more information, see the SageMaker API documentation for CreateTransformJob. Some examples: “$[1:]”, “$.features” (default: None).
output_filter (str or Placeholder): A JSONPath to select a portion of the joined/original output to return as the output. For more information, see the SageMaker API documentation for CreateTransformJob. Some examples: “$[1:]”, “$.prediction” (default: None).
join_source (str or Placeholder): The source of data to be joined to the transform output. It can be set to ‘Input’ meaning the entire input record will be joined to the inference result. You can use OutputFilter to select the useful portion before uploading to S3. (default: None). Valid values: Input, None.
parameters(dict, optional): The value of this field is merged with other arguments to become the request payload for SageMaker `CreateTransformJob<https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateTransformJob.html>`_.
You can use `parameters` to override the value provided by other arguments and specify any field's value dynamically using `Placeholders<https://aws-step-functions-data-science-sdk.readthedocs.io/en/stable/placeholders.html?highlight=placeholder#stepfunctions.inputs.Placeholder>`_.
"""
if wait_for_completion:
"""
Example resource arn: arn:aws:states:::sagemaker:createTransformJob.sync
"""
kwargs[Field.Resource.value] = get_service_integration_arn(
SAGEMAKER_SERVICE_NAME, SageMakerApi.CreateTransformJob,
IntegrationPattern.WaitForCompletion)
else:
"""
Example resource arn: arn:aws:states:::sagemaker:createTransformJob
"""
kwargs[Field.Resource.value] = get_service_integration_arn(
SAGEMAKER_SERVICE_NAME, SageMakerApi.CreateTransformJob)
if isinstance(job_name, str):
transform_parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type,
job_name=job_name,
input_filter=input_filter,
output_filter=output_filter,
join_source=join_source)
else:
transform_parameters = transform_config(
transformer=transformer,
data=data,
data_type=data_type,
content_type=content_type,
compression_type=compression_type,
split_type=split_type,
input_filter=input_filter,
output_filter=output_filter,
join_source=join_source)
if isinstance(job_name, Placeholder):
transform_parameters['TransformJobName'] = job_name
transform_parameters['ModelName'] = model_name
if experiment_config is not None:
transform_parameters['ExperimentConfig'] = experiment_config
if tags:
transform_parameters['Tags'] = tags if isinstance(
tags, Placeholder) else tags_dict_to_kv_list(tags)
if Field.Parameters.value in kwargs and isinstance(
kwargs[Field.Parameters.value], dict):
# Update transform_parameters with input parameters
merge_dicts(transform_parameters, kwargs[Field.Parameters.value])
kwargs[Field.Parameters.value] = transform_parameters
super(TransformStep, self).__init__(state_id, **kwargs)
def test_transform_config(sagemaker_session):
tf_transformer = transformer.Transformer(
model_name="tensorflow-model",
instance_count="{{ instance_count }}",
instance_type="ml.p2.xlarge",
strategy="SingleRecord",
assemble_with="Line",
output_path="{{ output_path }}",
output_kms_key="{{ kms_key }}",
accept="{{ accept }}",
max_concurrent_transforms="{{ max_parallel_job }}",
max_payload="{{ max_payload }}",
tags=[{
"{{ key }}": "{{ value }}"
}],
env={"{{ key }}": "{{ value }}"},
base_transform_job_name="tensorflow-transform",
sagemaker_session=sagemaker_session,
volume_kms_key="{{ kms_key }}",
)
data = "{{ transform_data }}"
config = airflow.transform_config(
tf_transformer,
data,
data_type="S3Prefix",
content_type="{{ content_type }}",
compression_type="{{ compression_type }}",
split_type="{{ split_type }}",
)
expected_config = {
"TransformJobName": "tensorflow-transform-%s" % TIME_STAMP,
"ModelName": "tensorflow-model",
"TransformInput": {
"DataSource": {
"S3DataSource": {
"S3DataType": "S3Prefix",
"S3Uri": "{{ transform_data }}"
}
},
"ContentType": "{{ content_type }}",
"CompressionType": "{{ compression_type }}",
"SplitType": "{{ split_type }}",
},
"TransformOutput": {
"S3OutputPath": "{{ output_path }}",
"KmsKeyId": "{{ kms_key }}",
"AssembleWith": "Line",
"Accept": "{{ accept }}",
},
"TransformResources": {
"InstanceCount": "{{ instance_count }}",
"InstanceType": "ml.p2.xlarge",
"VolumeKmsKeyId": "{{ kms_key }}",
},
"BatchStrategy": "SingleRecord",
"MaxConcurrentTransforms": "{{ max_parallel_job }}",
"MaxPayloadInMB": "{{ max_payload }}",
"Environment": {
"{{ key }}": "{{ value }}"
},
"Tags": [{
"{{ key }}": "{{ value }}"
}],
}
assert config == expected_config
