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

feat: SemiSupervised Training Mixin class #3164

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

ori-kron-wis
Copy link
Collaborator

@ori-kron-wis ori-kron-wis commented Jan 27, 2025

use what @ethanweinberger already made as a basis to semisupervisedtrainingmixin
We would like to add more functionality to it (e.g: interoperability)

@ori-kron-wis ori-kron-wis self-assigned this Jan 27, 2025
@ori-kron-wis ori-kron-wis added the on-merge: backport to 1.2.x on-merge: backport to 1.2.x label Jan 27, 2025
@ori-kron-wis ori-kron-wis added this to the scvi-tools 1.2 milestone Jan 27, 2025
Copy link

codecov bot commented Jan 27, 2025

Codecov Report

Attention: Patch coverage is 61.64384% with 28 lines in your changes missing coverage. Please review.

Project coverage is 82.53%. Comparing base (dad5cd9) to head (32c4f7e).

Files with missing lines Patch % Lines
src/scvi/model/base/_training_mixin.py 58.20% 28 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #3164      +/-   ##
==========================================
- Coverage   82.67%   82.53%   -0.14%     
==========================================
  Files         185      185              
  Lines       16205    16241      +36     
==========================================
+ Hits        13397    13405       +8     
- Misses       2808     2836      +28     
Files with missing lines Coverage Δ
src/scvi/model/_scanvi.py 94.06% <100.00%> (-1.18%) ⬇️
src/scvi/model/base/__init__.py 100.00% <100.00%> (ø)
src/scvi/model/base/_training_mixin.py 71.00% <58.20%> (-26.15%) ⬇️

@ori-kron-wis ori-kron-wis marked this pull request as ready for review February 18, 2025 16:14
If True, run the integrated circuits interpretability per sample and returns a score
matrix, in which for each sample we score each gene for its contribution to the
sample prediction
shap_values
Copy link
Member

Choose a reason for hiding this comment

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

have you tried it? does it take forever?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I guess I need to also check for large dataset.
IG works fast , shap is dependent on the number of classes

@ori-kron-wis ori-kron-wis added on-merge: backport to 1.3.x on-merge: backport to 1.3.x and removed on-merge: backport to 1.2.x on-merge: backport to 1.2.x labels Feb 25, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
on-merge: backport to 1.3.x on-merge: backport to 1.3.x
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants