In this chapter, we showed how to use SageMaker Data Wrangler using a telco customer churn dataset. We learned how to import data from various sources, join tables, analyze with advanced ML-based analyses, and create visualizations with SageMaker Data Wrangler. We then applied transformations easily with built-in transforms available out of the box from SageMaker Data Wrangler without any code. At the end of the chapter, we showed how to export the transformed data to an S3 bucket and how to easily train an ML model using the automatically generated notebook.

In the next chapter, we will learn about the concept of a feature store in a machine learning project, and how to set up a feature store using SageMaker Feature Store. SageMaker Feature Store unifies the features across teams so that teams can remove redundant feature engineering pipelines. It also serves as a central repository for both model training and model serving use cases because of its unique design pattern...