Machine Learning with Django logo ML with Django

Demand for Machine Learning (ML) applications is growing. Many resources show how to train ML algorithms. However, the ML algorithms work in two phases:

The benefits for business are in the inference phase when ML algorithms provide information before it is known. There is a technological challenge on how to provide ML algorithms for inference into production systems. There are many requirements which need to be fulfilled:

There are many ways of how ML algorithms can be used:

This tutorial provides code examples on how to build your ML system available with REST API. In this tutorial, for building the ML service I will use Python 3.6 and Django 2.2.4. This tutorial is the first part that covers the basics which should be enough to build your ML system which:

There is an advanced tutorial in preparation that covers following topics:

In my opinion, building your ML system has a great advantage - it is tailored to your needs. It has all features that are needed in your ML system and can be as complex as you wish.

This tutorial is for readers who are familiar with ML and would like to learn how to build ML web services. Basic Python knowledge is required. The full code of this tutorial is available at: https://github.com/pplonski/my_ml_service.

Next step: Start Django Project


Ad: React and Django tutorial

You might find interesting our tutorial on how to create Software-as-a-Service (SaaS) application from scratch. In the course, we build a web service for server uptime monitoring. It notifies users by email in case of a server down-event. Additionally, it uses Machine Learning for anomaly detection in server’s response time (models training done in Celery background task). It teaches you React & Django development and app cloud deployment. You can read more here and on the course website.