Movie Lens

The movie lens database is a collection of data built on users’ reviews of movies. It is one of the most popular open datasets out there. We can easily download the 100K version by using Google. It is different in the way that the data isn’t found in an Excel format but is available in plaintext. This makes it easy to parse. We’ve seen that pandas makes parsing Excel files easy, but many programming languages don’t have this feature.

Download the data and take a look. There is a large amount of data, and we’ll only work with a small subset.

Open the first file we will work with, u.item: