9 Putting your code into production
- Pipeline to store model predictions in a database table
- Credentials protection in code
- Application Programming Interfaces
The concepts of this chapter are important for many applications where you need to put data science-related code into production. Consider the following scenarios:
9.1 Putting a machine learning model into production
9.2 Creating a machine learning pipeline
9.2.1 Creating a prototype pipeline
9.2.2 Generalizing the pipeline: training the machine learning model
9.2.3 Fetching predictions offline
9.2.4 How to protect your credentials in your code
9.3 How to convert your code into an API
9.3.1 Overview of APIs
9.3.2 Creating an API
9.4 Practice on your own
9.5 Summary