Skip to content

Fix Riemannian potato tutorial plot behavior#1011

Merged
bruAristimunha merged 12 commits intodevelopfrom
fix/issue-997-potato-plot
Mar 3, 2026
Merged

Fix Riemannian potato tutorial plot behavior#1011
bruAristimunha merged 12 commits intodevelopfrom
fix/issue-997-potato-plot

Conversation

@bruAristimunha
Copy link
Collaborator

@bruAristimunha bruAristimunha commented Mar 1, 2026

Summary

  • handle Potato / PotatoField prediction label encodings robustly via _predict_clean_mask
  • simplify the tutorial using pyRiemann PR423 enhancements in PotatoField:
    • per-potato metrics via metric=[...]
    • custom method_combination for min(Fisher, Stouffer)
    • remove manual per-potato fitting/combination loops
  • improve the 2D potato visualization to better match the pyRiemann style (offline calibration, Oz/C4 projection, clearer scaling/styling)
  • clarify the RPF concept text for dependent per-potato p-values
  • point pyriemann dependency to GitHub source (master) to include the new API

Fixes #997

Validation

  • python -m py_compile examples/advanced_examples/plot_riemannian_artifact_rejection.py
  • tomllib parse check for pyproject.toml

@chatgpt-codex-connector
Copy link

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

- handle Potato/PotatoField predict label encodings robustly\n- align 2D potato plot with pyRiemann-style offline calibration and clearer channels\n- clarify RPF combined-score wording for dependent p-values
@bruaris bruaris force-pushed the fix/issue-997-potato-plot branch from 37e876b to 65d1505 Compare March 1, 2026 20:01
Use pyRiemann PR423 capabilities (per-potato metric and custom method_combination) to replace manual iRPF combination logic, and point pyriemann dependency to GitHub source for the new API.
bruAristimunha and others added 5 commits March 2, 2026 13:28
Co-authored-by: Quentin Barthélemy <q.barthelemy@gmail.com>
Signed-off-by: Bru <b.aristimunha@gmail.com>
Co-authored-by: Quentin Barthélemy <q.barthelemy@gmail.com>
Signed-off-by: Bru <b.aristimunha@gmail.com>
Rename all 5 call sites from _predict_clean_mask to predict_clean_mask
to match the function definition on line 111.
@qbarthelemy
Copy link
Contributor

Can you share here the corrected potato plot?

@bruAristimunha
Copy link
Collaborator Author

Sure, it is here:

https://github.com/NeuroTechX/moabb/actions/runs/22577873561/artifacts/5722162582

image

bruAristimunha and others added 2 commits March 2, 2026 19:30
Co-authored-by: Quentin Barthélemy <q.barthelemy@gmail.com>
Signed-off-by: Bru <b.aristimunha@gmail.com>
…ontours

Replace dense 20-level contourf across the entire z-score map with a
two-layer strategy: filled contours masked to inside the potato (z<=3),
sparse dashed grey outline contours outside, and a prominent black
boundary line. This makes the potato boundary much easier to distinguish.
@bruAristimunha bruAristimunha merged commit f3c6d8f into develop Mar 3, 2026
14 checks passed
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.

Riemannian artefacts rejection tutorial plot

2 participants