Using Batch Transform for inference

In the previous recipe, we trained and deployed a BlazingText model that accepts a string statement and returns whether the statement is POSITIVE or NEGATIVE. In this recipe, we will use this model along with the Batch Transform capability of SageMaker to perform text classification on the entire test dataset all at the same time without having a persistent inference endpoint.

Getting ready

Here are the prerequisites for this recipe:

• This recipe continues from Training and deploying a BlazingText model.
• A SageMaker Studio notebook running the Python 3 (Data Science) kernel.

How to do it…

The steps in this recipe focus on using the prerequisites we prepared in the previous recipes to run a Batch Transform job using the SageMaker Python SDK:

1. Create a new notebook using the Python 3 (Data Science) kernel inside the my-experiments/chapter08 directory and rename it to the name of this recipe. When prompted for...