In this project, I will be using machine learning to classify a song as popular or not popular. The dataset used in this project is called million song dataset. As the name suggests, dataset contains one million contemporary music tracks from 1920s to 2010.
In order to run the jupyter notebook, you will need csv file with all the data in it. You can get that file from here. Place this file in assets directory, then you can run the jupyter notebook. If you just want to look at the results then take a look at the slides
- Thierry Bertin-Mahieux, Daniel P.W. Ellis, Brian Whitman, and Paul Lamere. The Million Song Dataset. In Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011), 2011.