The Million Song Dataset Challenge aims at being the best possible offline evaluation of a music recommendation system.
million-songss.py
It is the executed file. After running it, each user will have a recomendation of 500 songs.
map_evaluation.py
This is an evaluation file. We use mAP(mean average precision) as the evaluation metric.
Before running the code, you need to download the dataset from
http://labrosa.ee.columbia.edu/millionsong/tasteprofile "getting the code"
How to run the code
python million-songss.py
python map_evaluation.py