Skip to content

Conversation

@mbrotos
Copy link
Owner

@mbrotos mbrotos commented Jun 25, 2025

As per the candidate apporach, we should only count performance metrics on a per-table basis using test examples where gt_table is equal to the table we are assessing. Thus, FP and TN should be zero.

@mbrotos mbrotos requested review from DrRakha and Copilot June 25, 2025 21:55
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This pull request updates the performance metric calculations so that false positives (FP) and true negatives (TN) are explicitly set to zero, adhering to the candidate approach which focuses on per-table evaluations with test examples.

  • Removed the FP join and summarisation block and replaced it with a constant assignment.
  • Removed the TN join and summarisation block and replaced it with a constant assignment.

@mbrotos mbrotos closed this Jun 30, 2025
@mbrotos mbrotos deleted the metric-fix branch June 30, 2025 14:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant