pickle and Flask

A machine learning model can “live” in (be part of) many different environments. The choice of environment should depend on the type of application that is being developed, the performance requirements, and the expected frequency of updates. For example, a model that has to predict the weather once per day for a weather analyst has different requirements than a model that makes friend suggestions for millions of people on a social network.

For extreme cases, there are specialized techniques such as streaming models. We’ll have a look at them later in this chapter. For now, we’ll focus on a method that works for most use cases: running a model as part of an API. In doing so, our model can be part of a microservices architecture, which gives a lot of flexibility and scalability. To build such an API, pickle and joblib are two popular libraries that can be used when working with Python models. They offer the possibility to capture a dataset...