mmcdermott MEDS_transforms issues

mmcdermott / MEDS_transforms

A simple set of MEDS polars-based ETL and transformation functions

MIT License

15 stars 3 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

add_time_derived_measurements breaks if you use _script in the meds_transform_runner

#202 Oufattole opened 4 days ago
1
All stages must have unique names or an error should be thrown.

#201 mmcdermott opened 4 days ago
0
Stages that depend on code metadata having been recently computed (e.g., `filter_measurements`) should be better documented

#200 mmcdermott opened 4 days ago
1
Hotfix 0.0.8

#199 mmcdermott closed 5 days ago
2
Tokenization Stage Misalignment Fix

#198 Oufattole closed 5 days ago
2
Misalignment Between Static and Event Sequence DataFrames

#197 Oufattole closed 5 days ago
2
Add wget blocks to run.sh for MIMIC and eICU pipelines

#196 coderabbitai[bot] opened 6 days ago
0
Should distribute / package typing information too

#195 mmcdermott opened 1 week ago
1
Lock files should be pipeline ID specific in some way -- this will enable pipelines to flag when old run locks are present.

#194 mmcdermott opened 1 week ago
0
Release Candidate 0.0.7

#193 mmcdermott closed 6 days ago
2
Add appropriate dots into MIMIC metadata files for omop matching.

#192 mmcdermott closed 1 week ago
2
Upgraded polars and set infer schema to false for metadata extraction.

#191 mmcdermott closed 1 week ago
2
`extract_code_metadata.py` should read in columns contributing to descriptions or parent codes as strings rather than inferring their types.

#190 mmcdermott closed 1 week ago
0
Various MIMIC-IV fixes and improvements

#189 mmcdermott closed 1 week ago
2
The unzipping solution causes errors if files have already been unzipped in the MIMIC-IV example

#188 mmcdermott closed 1 week ago
0
Adds a runner to run an entire pipeline in one command, with optional support for customized per-stage parallelization instructions.

#187 mmcdermott closed 1 week ago
2
Metadata extraction should log a warning if code-part column names are not uniformly either extracted or not extracted across metadata sources.

#186 mmcdermott opened 1 week ago
0
Adds a test case to document the behavior for #156.

#185 mmcdermott closed 1 week ago
2
Refactors and adds stage-specific extraction tests to enable more targeted testing of metadata extraction pipeline improvements.

#184 mmcdermott closed 1 week ago
2
MEDS-Extract Tests should be re-factored and split into multiple single-stage tests and one full-pipeline test

#183 mmcdermott closed 1 week ago
0
Duplication between `text_value` and `numeric_value` should be ignored when possible.

#182 mmcdermott closed 1 week ago
0
The MIMIC ETL does not fully normalize parent codes to omop vocabs.

#181 mmcdermott closed 1 week ago
2
Should pull the generic hydra resolvers (e.g., `get_script_docstring`) into a separate package

#180 mmcdermott opened 1 week ago
0
Improve tests and test coverage.

#179 mmcdermott closed 1 week ago
2
MEDS-transforms should be usable under python 3.11 as well as 3.12

#178 mmcdermott closed 1 week ago
2
We need a more robust interface for ways of (a) processing numerical and categorical values and (b) normalizing output data in light of those modes.

#177 mmcdermott opened 1 week ago
5
See if we can support Python 3.11

#176 mmcdermott closed 1 week ago
0
Release Candidate 0.0.6

#175 mmcdermott closed 1 week ago
2
There should be an immediate way to identify when an entire stage has completed so entire pipelines can more directly short-circuit

#174 mmcdermott closed 1 week ago
1
Updating to MEDS v0.3.2 by correcting the subject ID field name.

#173 mmcdermott closed 1 week ago
2
Make compatible with MEDS v0.3.2

#172 mmcdermott closed 1 week ago
0
Added badges to the README.

#171 mmcdermott closed 2 weeks ago
2
Add badges to README

#170 mmcdermott closed 2 weeks ago
0
DO NOT SUBMIT

#169 mmcdermott closed 3 weeks ago
2
If a shard is empty, tensorization crashes.

#168 mmcdermott closed 3 weeks ago
0
Adds a multi-stage integration test for pre-processing.

#167 mmcdermott closed 3 weeks ago
2
Fixes and expands tests for `aggregate_code_metadata` across various aggregations

#166 mmcdermott closed 3 weeks ago
2
Using `do_summarize_all_codes` with `values/quantile` object configuration breaks the mapper

#165 mmcdermott closed 3 weeks ago
0
Error message when `aggregate_code_metadata.py` gets an aggregation that should be an object but is just a string should be clearer.

#164 mmcdermott opened 3 weeks ago
0
Aggregation integration test should cover all integrations

#163 mmcdermott closed 3 weeks ago
0
aggregate_code_metadata Quantile Binning CLI Bug

#162 Oufattole closed 3 weeks ago
1
Metadata input dir may be being set improperly to the last metadata stage's output directory instead of the `reducer_output_dir`

#161 mmcdermott closed 3 weeks ago
1
Multi-stage integration tests for pre-processing stages in sequence should be added.

#160 mmcdermott closed 3 weeks ago
0
Fix tests to expect Float32 throughout and time derived to specifically compute age in float32

#159 mmcdermott closed 3 weeks ago
2
Typing should use Float32 Throughout

#158 mmcdermott closed 3 weeks ago
1
Remove aggregation of code metadata from default extraction ETL.

#157 mmcdermott closed 3 weeks ago
2
Metadata extraction does not appear to be extracting some columns correctly

#156 mmcdermott closed 1 week ago
4
Pipeline Configuration Improvements

#155 mmcdermott opened 3 weeks ago
1
Exit metadata extraction if there is no _metadata in the event configs

#154 prenc closed 3 weeks ago
5
`reshard_to_split` should (in a configurable manner) sub-shard the input rather than re-shard the input where possible.

#153 mmcdermott opened 3 weeks ago
0