Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat(bootstrap): generate confidence interval with bootstrap #21

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
Draft

feat(bootstrap): generate confidence interval with bootstrap #21

wants to merge 2 commits into from

Conversation

shenxiangzhuang
Copy link
Contributor

Close #20

@shenxiangzhuang shenxiangzhuang marked this pull request as draft December 14, 2024 13:19
shenxiangzhuang
shenxiangzhuang commented Dec 14, 2024
View reviewed changes
Copy link
Contributor Author

@shenxiangzhuang shenxiangzhuang left a comment

Choose a reason for hiding this comment

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

Please give some suggestions about this implementation and I'd like to improve it further.

python/evalica/__init__.py Outdated
@@ -998,6 +998,83 @@ def pairwise_frame(scores: pd.Series[float]) -> pd.DataFrame:
return pd.DataFrame(pairwise_scores(scores.to_numpy()), index=scores.index, columns=scores.index)


@dataclass
class BootstrapConfidenceInterval:
score_method: Literal['elo', 'bradley-terry', 'newman'] # TODO: more?
Copy link
Contributor Author

Choose a reason for hiding this comment

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

@dustalov Shall we support more methods here?

python/evalica/__init__.py Show resolved Hide resolved
@dustalov
Copy link
Owner

As mentioned in #20, I recommend taking a step back from rushing into implementing the idea and instead focusing on developing the API usage examples first.

It might be best to structure this as a wrapper function around the score computation function, ensuring it remains flexible and not tied to specific arguments passed to the estimator.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Generate confidence interval with bootstrap
2 participants
@shenxiangzhuang @dustalov