Deploy a Machine Learning Model as a Web Application (Part 2)

This is the second part in a two-part series. I suggest you read the first part first. Interact with the app via the App link

The goal of the second part of this tutorial series is to deploy the machine learning wine quality prediction web application built in part 1—this time in the cloud.

If you haven’t already, I’d recommend checking out part one, which you can do here: Deploy a Machine Learning Model as a Web Application (Part 1)

In order to have a smooth ride during this deployment stage, it’s always good to follow best practices by designing a system architecture that integrates all the basic units together. Below is the designed machine learning system architecture for this project.

Deployment system architecture

Prerequisites

Looking at the deployment system architecture above, there will be a need for us to:

• Use a version control platform (GitHub)
• Have a free Heroku account set up

Version Control

Version control is a system that records changes to a file or set of files over time so that you can recall specific versions later. There are several version control platforms, but the choice for this project, based on the designed deployment architecture, is GitHub.

GitHub is a Git repository hosting service, but it adds many of its own features. While Git is a command-line tool, GitHub provides a web-based graphical interface. It also provides access control and several collaboration features, such as wikis and basic task management tools for every project.

To start with GitHub, you’ll need to create a free account, which you can do via GitHub’s signup…