Fix repeat times in evaluation #410
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Summary of ChangesHello @chenyushuo, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the evaluation capabilities by introducing 'evaluation at k' metrics. This allows for a more detailed understanding of model performance across different prediction horizons or sample sizes. The changes involve updating core configuration structures, refining metric calculation logic, and ensuring these new metrics are correctly processed and logged, ultimately providing richer insights into model behavior during evaluation. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a flexible evaluation mechanism using the eval_at_k configuration, allowing for more detailed metrics like mean@k, best@k, and worst@k. The changes are well-integrated across configuration, data processing, and metric calculation components. However, I've identified a critical issue in the calculation of best@k and worst@k metrics, and a potential crash scenario if eval_at_k is misconfigured as an empty list. Addressing these issues will ensure the new feature is robust and correct.
Collaborator
Author
|
/unittest-all |
Collaborator
|
/unittest-all |
pan-x-c
reviewed
Nov 26, 2025
Summary
Failed Tests
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-module-explorer |
Summary
Skipped
Tests
Github Test Reporter by CTRF 💚 |
pan-x-c
approved these changes
Nov 26, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
As the title says.
Checklist
Please check the following items before code is ready to be reviewed.