recommenders-team/recommenders

[ASK] How do you get the recommendations from NAML?

Open

#2,036 opened on Nov 8, 2023

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (2,972 forks)batch import
help wanted

Repository metrics

Stars
 (17,706 stars)
PR merge metrics
 (Avg merge 6d 16h) (10 merged PRs in 30d)

Description

Description

I want to investigate which articles the model recommends. I can't grasp what to do after training because it just shows how to evaluate it unless I am missing something. It outputs a prediction file but it looks like it's supposed to be for the MIND competition? and it predicts everything.

I am wondering if it is possible to predict articles for one user. There doesn't seem to be a clear, usable function, and I don't quite understand the get pred function from the base model.

Basically, can I predict the articles by feeding impression data? or somehow modifying it?

Other Comments

I want to try using NAML and feed it with my own dataset to study. I am currently figuring out how it might work potentially in production.

Contributor guide

Research direction
Examine the NAML model's predict method and the get pred function. Look at how the prediction file is generated and see if you can adapt it for single user predictions.
Tech stack
python
Domain
backend
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Unclear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75