feat: Graph dataloader in scviva-tools - #8
Conversation
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 5e87b17182
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| return GraphDataLoader( | ||
| self.adata_manager, | ||
| full_adata_manager=self.adata_manager, | ||
| indices=indices, |
There was a problem hiding this comment.
Preserve semisupervised loader kwargs in graph splitter
This always instantiates GraphDataLoader, so any semisupervised-only kwargs that DataSplitter normally forwards to SemiSupervisedDataLoader (for example n_samples_per_label) are now passed into AnnDataLoader instead and can raise TypeError during training. This is a regression for semisupervised ResolVI workflows that previously relied on label-resampling behavior when labels are registered.
Useful? React with 👍 / 👎.
…d spatial quality benchmarks for GraphDataLoader vs AnnDataLoader
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Description
Brief description of changes and motivation.
Type of Change
Testing
pytest tests/ -v)Checklist
ruff check src/ tests/)