© Ramcharan Kakarla, Sundar Krishnan and Sridhar Alla 2021
R. Kakarla et al.Applied Data Science Using PySparkhttps://doi.org/10.1007/978-1-4842-6500-0_9

9. Deploying Machine Learning Models

Ramcharan Kakarla1  , Sundar Krishnan1 and Sridhar Alla2
(1)
Philadelphia, PA, USA
(2)
New Jersey, NJ, USA
 
This chapter will educate you on best practices to follow when deploying a machine learning model. We will use three methods to demonstrate the production deployment, as follows:
  • Model deployment using HDFS object and pickle files

  • Model deployment using Docker

  • Real-time scoring API

In the previous chapter, you got a glimpse of the first technique. In this section, we will cover it in more detail. The code provided is the starter code to build the model and evaluate ...

Get Applied Data Science Using PySpark: Learn the End-to-End Predictive Model-Building Cycle now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.