This tutorial implements the following AWS architecture for handling a SageMaker Batch Transformer.
The transformer generates an event that kicks off a Lambda function. The transformer generates the model inputs and predictions used by the lambda function.
A separate process is assumed to process actuals as they are received in the system.
The below file is a Jupyter notebook file that should be uploaded the the Sagemaker Notebook Instance.
The Notebook file builds a lambda package in a Gzip to upload to AWS. The below file is the Lambda python function, this should be uploaded to a SageMaker Notebook Instance along with the above notebook.