Python Programming: Build a Recommendation Engine in Django

Learn to build a powerful recommendation engine with Django and machine learning! This course guides you through creating a system that automatically suggests movies to users based on their ratings. We'll leverage collaborative filtering, a popular machine learning technique, to deliver personalized recommendations.

This project focuses on scalability, implementing batch inference using Celery, a robust background worker process. Celery, combined with Django, allows you to run tasks asynchronously, making your recommendation engine capable of handling thousands of users efficiently. You'll gain a deep understanding of how to schedule and manage tasks for background processing.

We'll utilize the widely-used MovieLens dataset, a CSV file perfect for machine learning tutorials. However, the key differentiator of this course is learning to load this data into a SQL database using a Django model. Discover the advantages of SQL databases over CSV files for performance and data management.

Enhance user interaction with HTMX, a revolutionary approach to dynamic web development. HTMX enables you to update content – like rating movies – without full page reloads, providing a smoother user experience with minimal JavaScript. You'll see practical applications of HTMX for rating, sorting, and loading movie data.

The recommendation engine is structured into three key components:

• Web Process (Django): Collects user ratings and serves recommendations when available.
• Machine Learning Pipeline: Extracts, transforms, and trains a collaborative filtering model using the data.
• Worker Process (Celery): Schedules and executes the trained model predictions to update user recommendations.

Prerequisites:

• Python 3.6+ (e.g., "30 Days of Python")
• Django 3.2+ (e.g., "Your First Django Web Project" or "Try Django 3.2")
• Celery with Django (e.g., "Time & Tasks 2" or [this blog post](link to blog post))