Skip to content

38 add data loaders for common first order datasets#77

Merged
pwhofman merged 2 commits intomainfrom
38-add-data-loaders-for-common-first-order-datasets
Apr 17, 2025
Merged

38 add data loaders for common first order datasets#77
pwhofman merged 2 commits intomainfrom
38-add-data-loaders-for-common-first-order-datasets

Conversation

@pwhofman
Copy link
Copy Markdown
Owner

No description provided.

@pwhofman pwhofman requested a review from Copilot April 17, 2025 18:10
@pwhofman pwhofman self-assigned this Apr 17, 2025
@pwhofman pwhofman linked an issue Apr 17, 2025 that may be closed by this pull request
Copy link
Copy Markdown
Contributor

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.

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

Comment thread src/probly/metrics.py
Comment on lines +138 to +139
covered = preds[np.arange(preds.shape[0]), targets]
ceff = np.mean(preds[covered])
Copy link

Copilot AI Apr 17, 2025

Choose a reason for hiding this comment

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

The indexing in the 2D case appears incorrect. 'covered' is derived from selecting values via np.arange and targets, so using it directly to index preds may not produce the intended boolean mask of covered instances. Consider revising the logic to compute the set size or to use an appropriate boolean mask representing covered predictions.

Suggested change
covered = preds[np.arange(preds.shape[0]), targets]
ceff = np.mean(preds[covered])
covered = preds[np.arange(preds.shape[0]), targets] == targets
ceff = np.mean(np.sum(preds[covered], axis=1))

Copilot uses AI. Check for mistakes.
@pwhofman pwhofman merged commit 44a9f9a into main Apr 17, 2025
7 checks passed
@pwhofman pwhofman deleted the 38-add-data-loaders-for-common-first-order-datasets branch April 17, 2025 18:14
elias0224 pushed a commit to elias0224/probly that referenced this pull request Oct 30, 2025
* Add covered efficiency metric

* Add ImageNet-ReaL and multiple DCICDatasets
davyddzhalaiansamani pushed a commit to D4V1ND/probly that referenced this pull request Dec 10, 2025
* Add covered efficiency metric

* Add ImageNet-ReaL and multiple DCICDatasets
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.

Add data loaders for common first-order datasets

2 participants