Chapter 11: Scheduling Regular Inferences
In the previous chapter, you trained a model and visualized the events it was able to detect over an evaluation period. Once Amazon Lookout for Equipment has trained a model, you can configure and start an inference scheduler that will run your data against it. This scheduler will wake up regularly, look for CSV files in a location on Amazon S3, open the right ones, and run them with your trained model to predict whether anomalous events are present in your new data. This process is called inference.
In this chapter, you will learn how to manage such schedulers and how to use the predictions obtained. In other words, you will learn how to use a deployed version of your model and use it in production.
In this chapter, we're going to cover the following main topics:
- Using a trained model
- Configuring a scheduler
- Preparing a dataset for inference
- Extracting the inference results