how to preprocess the amazon book data?
Cloudcatcher888 opened this issue · 1 comments
Cloudcatcher888 commented
how to preprocess the amazon book data?
cenyk1230 commented
Hi @Cloudcatcher888,
Thank you for your attention to our work.
I add the preprocessing code in the preprocess/ directory. You should first download the original data from http://jmcauley.ucsd.edu/data/amazon/index.html, and then run python preprocess/data.py to preprocess the Amazon Book dataset. If you want to compute the diversity in the experiment, you also need to run python preprocess/category.py to generate the corresponding category information.