Invoking machine learning models with Amazon Athena using SQL queries

Amazon Athena is a serverless interactive query service that helps us analyze data in Amazon S3 using SQL syntax. As it is a serverless service, machine learning practitioners no longer need to manage any infrastructure, so we can focus on the work that needs to be done. If you have used or heard of Amazon Athena before, you must be aware that this solution can easily scale and support big data requirements. Amazon Athena also supports a variety of data formats (such as CSV and text files), columnar formats (such as Parquet and ORC), and compressed data formats (such as Snappy and GZIP).

Note

Of course, this is a simplified description of what serverless is all about. Feel free to check https://aws.amazon.com/serverless/ for more information.

In this recipe, we will use Amazon Athena to analyze our dataset stored in Amazon S3 using SQL statements. We will make use of a deployed machine learning model within...