Reimplement emd #48
Merged
Reimplement emd #48
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ghar1821
commented
Apr 16, 2025
| # A relatively short label, used when rendering visualisarions (required) | ||
| label: EMD Mean | ||
| label: EMD Mean CT |
There was a problem hiding this comment.
@LuLeom I expanded the return values to 4. So now we have mean and max calculated across all cell types, then mean and max across donors (see EMD Mean DN). See comment on the implementation in script.py file. I'll explain there.
ghar1821
commented
Apr 16, 2025
src/metrics/emd/script.py
Outdated
| emd_mean_ct = np.nanmean(emd_per_donor_per_ct.drop(columns=['cell_type', 'donor']).values) | ||
| emd_max_ct = np.nanmax(emd_per_donor_per_ct.drop(columns=['cell_type', 'donor']).values) | ||
|
|
||
| emd_mean_dn = np.nanmean(emd_per_donor_all_ct.drop(columns=['cell_type', 'donor']).values) |
There was a problem hiding this comment.
So the mean across donors is essentially the emd for all cell types then averaged across donors. I figured this will give a different emd information from emd_mean_ct in that emd_mean_ct is mean emd across the different cell types regardless of donors. While emd_mean_dn is mean emd across different donors regardless of cell types. I think it is a bit too complicated and we may have to think whether it makes sense to split it this way.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe your changes
Reimplemented EMD. Current implementation relies on cytonormpy. We no longer need it after this changes.
Also added EMD mean and max computed across all donors - probably need a better name.
Checklist before requesting a review
I have performed a self-review of my code
Check the correct box. Does this PR contain:
Proposed changes are described in the CHANGELOG.md
CI Tests succeed and look good!