Refactor analysis code #36
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
shchur
force-pushed
the
refactor-analysis-code
branch
from
5a0f38d to
abc9578
Compare
abdulfatir
requested changes
Sep 5, 2025
Collaborator
abdulfatir
left a comment
abdulfatir
left a comment
There was a problem hiding this comment.
Thanks @shchur! Overall looks okay to me. I left some comments and questions.
src/fev/analysis.py
Outdated
| Computes skill score (1 - geometric mean relative error) and win rate with bootstrap confidence | ||
| intervals across all tasks. Models are ranked by skill score. | ||
| Missing results are handled in 2 ways: |
Collaborator
There was a problem hiding this comment.
Maybe it would be helpful to specify what is the default strategy.
Contributor
Author
There was a problem hiding this comment.
I have refactored this logic to use the missing_strategy kwarg and the updated the docstring accordingly
src/fev/analysis.py
Outdated
| def pairwise_comparison( | ||
| summaries: SummaryType | list[SummaryType], | ||
| metric_column: str = "test_error", | ||
| task_columns: str | list[str] = "dataset_path", |
Collaborator
There was a problem hiding this comment.
Should this be "task_name"?
Contributor
Author
There was a problem hiding this comment.
Removed the task_columns from the API completely to always use all the default Task columns.
abdulfatir
approved these changes
Sep 5, 2025
src/fev/analysis.py
Outdated
| baseline_model: str | None = None, | ||
| ) -> pd.DataFrame: | ||
| """Compute the average score for each model for each task. | ||
| """Convert summaries into a pivot table with index equal to `task_columns` and columns equal to model names. |
Collaborator
There was a problem hiding this comment.
Can we update the docstring and preferably also the function name to indicate that this also scales by the baseline scores?
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.
Issue #, if available:
Description of changes:
leaderboard()andpairwise_comparison()to use skill scores + win rates, and report the CIs based on bootstrap.By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.