lyst / lightfm

A Python implementation of LightFM, a hybrid recommendation algorithm.
Apache License 2.0
4.66k stars 679 forks source link

Evaluate AUC on a subset of items #701

Open federico-fabiani opened 8 months ago

federico-fabiani commented 8 months ago

Hi everyone,

As from the title, I need to evaluate AUC for categories of items, in other words, I need to understand for a category (i.e. meat) if items with positive interactions score generally higher than negative ones. However, built-in auc metric requires the whole test set at once.

Is there a handy way to achieve what I need?