recommenders-team/recommenders

[ASK] Running evaluation on test set for DKN

Open

#1,807 opened on Aug 4, 2022

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've have been using DKN Deep Dive, but I wanted to add evaluation on the test data. When I run model.run_eval(test_file) I am getting an error. I believe this is because the test data has users that are not present in the training data.

I am using the small MIND dataset. But I split my training, validation and test data a little differently. Training is all of the small training data but the last day. Validation is the last day of the small training data Test is all of the small validation data.

Is this the expected behavior?

Other Comments

Contributor guide

Research direction
Check the DKN model's run eval method documentation and source code to understand its handling of unseen users; examine typical evaluation practices for recommendation models with cold start users.
Tech stack
python
Domain
backendmachine learning
Issue type
Research
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.
Mostly clear
Prerequisites
PythonRecommendation systems
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60