lyst / lyst/lightfm

Evaluate AUC on a subset of items

Open
#701 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
5.1k
Forks
724
PR merge metrics
No merged PRs in 30d

Description

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?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the built-in AUC metric and how it consumes the whole test set. Clarify how item categories would be supplied and how per-category results should be defined, then identify the relevant metric tests or entry points. Done should include a clear, tested way to evaluate AUC for a selected item category.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.