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.

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

Fix observed variable detection #1805

Closed
wants to merge 8 commits into from
Closed

Fix observed variable detection #1805

wants to merge 8 commits into from

Conversation

vitkl
Copy link
Contributor

@vitkl vitkl commented Nov 24, 2022

Create a separate method to detect observed sites and apply it everywhere necessary to automatically exclude observed sites.

Fixes #1801

@adamgayoso adamgayoso changed the title Fix observed variable detection #1801 Fix observed variable detection Nov 24, 2022
@codecov
Copy link

codecov bot commented Nov 24, 2022

Codecov Report

Base: 90.65% // Head: 90.43% // Decreases project coverage by -0.22% ⚠️

Coverage data is based on head (df52036) compared to base (3b687c0).
Patch coverage: 100.00% of modified lines in pull request are covered.

❗ Current head df52036 differs from pull request most recent head a81cd39. Consider uploading reports for the commit a81cd39 to get more accurate results

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1805      +/-   ##
==========================================
- Coverage   90.65%   90.43%   -0.23%     
==========================================
  Files         138      123      -15     
  Lines       10918    10283     -635     
==========================================
- Hits         9898     9299     -599     
+ Misses       1020      984      -36     
Impacted Files Coverage Δ
scvi/model/base/_pyromixin.py 94.44% <100.00%> (-0.91%) ⬇️
scvi/dataloaders/_ann_dataloader.py 89.39% <0.00%> (-4.55%) ⬇️
scvi/data/_preprocessing.py 74.80% <0.00%> (-1.71%) ⬇️
scvi/dataloaders/_anntorchdataset.py 91.17% <0.00%> (-1.48%) ⬇️
scvi/train/_trainingplans.py 93.76% <0.00%> (-0.70%) ⬇️
scvi/autotune/_manager.py 77.77% <0.00%> (-0.30%) ⬇️
scvi/data/_manager.py 98.25% <0.00%> (-0.23%) ⬇️
scvi/model/_scvi.py 95.94% <0.00%> (-0.11%) ⬇️
scvi/model/base/_base_model.py 93.22% <0.00%> (-0.09%) ⬇️
... and 58 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

Copy link
Member

@adamgayoso adamgayoso left a comment

Choose a reason for hiding this comment

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

What's the status of this @vitkl ?

@adamgayoso adamgayoso added this to the 0.20.0 milestone Dec 10, 2022
@vitkl
Copy link
Contributor Author

vitkl commented Dec 11, 2022

Still a work in progress, unfortunately, the solution I added doesn't seem to exclude observed variables. I will do a deeper dive some time this year.

@vitkl
Copy link
Contributor Author

vitkl commented Apr 7, 2024

I think this should be addressable by removing different procedures for different AutoGuide classes (#2695).

@vitkl vitkl closed this Apr 7, 2024
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.

Posterior sampling with Messenger Pyro guides -> huge memory use.
2 participants