Skip to content

[Nightly] add nn to nn tests; scale back reco tests#139

Merged
arokem merged 1 commit into
tractometry:mainfrom
36000:nightly_fixes_again
Jan 8, 2026
Merged

[Nightly] add nn to nn tests; scale back reco tests#139
arokem merged 1 commit into
tractometry:mainfrom
36000:nightly_fixes_again

Conversation

@36000

@36000 36000 commented Jan 8, 2026

Copy link
Copy Markdown
Collaborator

No description provided.

Copilot AI review requested due to automatic review settings January 8, 2026 19:14

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Pull request overview

This PR enhances the nightly test suite by adding neural network (nn) dependencies and optimizing reco test performance by reducing seed counts.

  • Adds nn extras to nightly test installation to ensure onnxruntime is available for neural network-based tests
  • Reduces n_seeds from 1,000,000 to 10,000 in reco tests to improve test execution time
  • Consolidates tracking parameter formatting in test_AFQ_reco80 for better readability

Reviewed changes

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

File Description
.github/workflows/nightly_test.yml Adds nn extras to pip install command to include onnxruntime dependency for neural network tests
AFQ/tests/test_api.py Reduces n_seeds from 1e6 to 1e4 in test_AFQ_reco and reformats tracking_params dict in test_AFQ_reco80 to single line

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread AFQ/tests/test_api.py
profile_weights="median",
bundle_info=abd.reco_bd(16),
tracking_params={"n_seeds": 1e6},
tracking_params={"n_seeds": 1e4},

Copilot AI Jan 8, 2026

Copy link

Choose a reason for hiding this comment

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

Using scientific notation (1e4) for n_seeds is inconsistent with the rest of the codebase, which uses integer literals (e.g., 250000 on line 286, 2000 on lines 749 and 900). Consider using the integer literal 10000 instead for consistency.

Copilot uses AI. Check for mistakes.
Comment thread AFQ/tests/test_api.py
tracking_params = dict(
odf_model="csd", n_seeds=10000, random_seeds=True, rng_seed=42
)
tracking_params = dict(odf_model="csd", n_seeds=1e4, random_seeds=True, rng_seed=42)

Copilot AI Jan 8, 2026

Copy link

Choose a reason for hiding this comment

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

Using scientific notation (1e4) for n_seeds is inconsistent with the rest of the codebase, which uses integer literals (e.g., 250000 on line 286, 2000 on lines 749 and 900). Consider using the integer literal 10000 instead for consistency.

Copilot uses AI. Check for mistakes.
@36000

36000 commented Jan 8, 2026

Copy link
Copy Markdown
Collaborator Author

@arokem what do you think, should we try these fixes out tonight to see if they fix the nightly reco tests?

@arokem

arokem commented Jan 8, 2026

Copy link
Copy Markdown
Member

Yeah, let's do it.

@arokem
arokem merged commit db57813 into tractometry:main Jan 8, 2026
15 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.

3 participants