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.

Sign up for GitHub

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

Jump to bottom

Match the MEDS label schema for MEDS dataset #72

Closed
Tracked by #92
mmcdermott opened this issue Jul 19, 2024 · 3 comments
Closed
Tracked by #92

Match the MEDS label schema for MEDS dataset #72

mmcdermott opened this issue Jul 19, 2024 · 3 comments
Labels
Impacts Benchmark Impacts the 2024 Summer / Fall Distributed MEDS Benchmarking Effort MEDS Compatibility Compatibility with the Medical Event Data Standard (MEDS) data schema priority:critical Things that are critical bug fixes, to be addressed immediately and pushed with minor version update Task DataFrame Format Relates to the output of a cohort extraction as well as how intermediates are stored Usability & Interface For things to make ACES more usable that don't involve fundamental configuration language changes
Milestone
MEDS Benchmarking...

Comments

@mmcdermott
Copy link
Collaborator

https://github.com/Medical-Event-Data-Standard/meds/blob/main/src/meds/schema.py#L67
@mmcdermott mmcdermott added the Impacts Benchmark Impacts the 2024 Summer / Fall Distributed MEDS Benchmarking Effort label Jul 22, 2024
@justin13601
Copy link
Owner

Add some renames at the end for col names, maybe a toggle for default vs. MEDS label

justin13601 added a commit that referenced this issue Jul 26, 2024
@justin13601
Rename index_timestamp as part of #72
b52a3ae
@justin13601 justin13601 mentioned this issue Jul 26, 2024
Merged
@mmcdermott mmcdermott added priority:critical Things that are critical bug fixes, to be addressed immediately and pushed with minor version update Usability & Interface For things to make ACES more usable that don't involve fundamental configuration language changes Task DataFrame Format Relates to the output of a cohort extraction as well as how intermediates are stored MEDS Compatibility Compatibility with the Medical Event Data Standard (MEDS) data schema labels Aug 6, 2024
This was referenced Aug 6, 2024
Closed
Open
@mmcdermott
Copy link
Collaborator Author

We'll want to explicitly validate against the imported MEDS schema, much as I do in MEDS transforms here: https://github.com/mmcdermott/MEDS_transforms/blob/main/src/MEDS_transforms/extract/finalize_MEDS_data.py#L15

Note this code may eventually move to the meds repo proper, per Medical-Event-Data-Standard/meds#37

justin13601 added a commit that referenced this issue Aug 12, 2024
@justin13601 @mmcdermott
Match MEDS label schema as per #72 (#80)
1bcd50b 
* Rename index_timestamp as part of #72

* Updated to overtly define in MEDS format. Not yet validated.

* Fixed expand_shards to work with arbitrary MEDS sharding strategies.

* Fixed a few other errors for MEDS v0.3 compatability. Now tested with config https://gist.github.com/mmcdermott/80a9086d8fdf36f2fd04b8e4912348ac on a tiny MIMIC cohort.

---------

Co-authored-by: Matthew McDermott <mattmcdermott8@gmail.com>
@justin13601
Copy link
Owner

Done in #80

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Impacts Benchmark Impacts the 2024 Summer / Fall Distributed MEDS Benchmarking Effort MEDS Compatibility Compatibility with the Medical Event Data Standard (MEDS) data schema priority:critical Things that are critical bug fixes, to be addressed immediately and pushed with minor version update Task DataFrame Format Relates to the output of a cohort extraction as well as how intermediates are stored Usability & Interface For things to make ACES more usable that don't involve fundamental configuration language changes
Projects
None yet
Milestone
MEDS Benchmarking Effort v0.0.1
Development

No branches or pull requests
2 participants
@mmcdermott @justin13601