A code-along Jupyter notebook for the Flatiron School Meetup, "The Science Behind Netflix Recommendations: Workshop", presented on:
- June 5, 2019
- October 21, 2019
The dataset used is The Movies Dataset found on Kaggle, specifically from the file ratings_small.csv: https://www.kaggle.com/rounakbanik/the-movies-dataset
The easiest way to see the code is by clicking here:
If you're reading the code in Binder, you won't be able to run codealong
, but you can view codealong-clean
.
If you do want to run the code on your own, download Jupyter Notebook and run these lines in your terminal:
git clone https://github.com/yishuen/meetup-movie-recommender.git
cd meetup-movie-recommender
jupyter notebook
I wrote a couple posts on Medium about recommendation engines: https://medium.com/@yishuen
A great book on big data. My favorite chapter is Chapter 9, and I highly recommend it if you want to understand how SVD works using gradient descent + Alternating Least Squares.
A couple really good podcast episodes that got me started with recommendation engines: