Correct 99.9% normalization to 100% normalization for "many-zero" columns #894
Conversation
This file contains 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
cliu72
requested changes
Feb 2, 2023
There was a problem hiding this comment.
This definitely solves the error that arises, but actually the correct behavior is for the function to ignore 0's when calculating the 99.9th percentile. For example, this is the mirroring code in create_pixel_matrix:
ark-analysis/ark/phenotyping/pixel_cluster_utils.py
Lines 780 to 782 in e6050fc
In that function, you are setting all 0's to nan, so the quantile function ignores those numbers. That's what we want here too.
alex-l-kong
requested review from
HPiyadasa
and removed request for
HPiyadasa
|
@HPiyadasa can you please approve this if it looks good? Need it so I can officially merge the changes in. |
HPiyadasa
approved these changes
Feb 9, 2023
github-merge-queue
bot
removed this pull request from the merge queue due to no response for status checks
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Outdated suggestions cannot be applied.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.
What is the purpose of this PR?
Closes #890. When an expression column for cell Pixie clustering is mostly zero, the 99.9% quantile value may equal 0, which will cause NaNs to appear for normalization. To prevent this, 100% quantile values should be set for those columns.
How did you implement your changes
Add correction in the way the normalization values are set in
CellSOMCluster.normalize_data. Define the normalization values prior to applying them tocell_data_sub.