turi-code / sample-movie-recommender

Sample for building a movie recommender with GraphLab Create.

Movie Recommender Sample Project

This is a sample for recommenders. Explore the gallery to see other examples.

This sample code shows how to build, evaluate, and deploy a recommender model for movies. You could use this model to power "Recommended for you" or suggest "Similar Movies" features.

Get started

1. Before you begin, make sure you have installed GraphLab Create, a Python package for machine learning.

2. Download and extract the example code to a directory on your machine, or clone it with the following command:

   git clone http://github.com/turi-code/sample-movie-recommender
   cd sample-movie-recommender

3. While in the sample-movie-recommender directory, run the following script to download the sample project data:

python download_data.py

4. Making sure you are working in a Python environment with GraphLab Create installed, run the movie_recommender.py script to build and explore the recommender model on your machine:

   python -i movie_recommender.py

   The -i flag causes Python to drop into an interactive interpreter after the script executes.

   Alternatively, you can also run the provided IPython Notebook:

   ipython notebook movie_recommender.ipynb

   Once the model has been created, a browser window should open to let you explore and interact with your recommender model:

   

Learn More and Next Steps

Once you have the sample project running, you can try the following:

• Learn more about how the sample works
• Try it on your own data set
• Use the model in your app

To find out more about building recommender models, check out the user guide or API documentation.

Troubleshooting

If you are having trouble, please create a Github Issue or start a discussion on the user forum.

Acknowledgements

The MovieLens dataset was collected by the GroupLens Research Project at the University of Minnesota.