Tidy up the ChestX-ray14 dataset for the PyHealth 2.0 release #777
+140
−2,736
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
… like the other unit tests (still generate fake images to avoid adding large files to the repo history)
…e directly from the NIH box share instead of from a mirror in a personal Google Drive
…e image processor is needed for the chestxray14 dataset
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Summary
In preparation for the PyHealth 2.0 release, this PR cleans up a few loose ends in the
ChestXray14Datasetdataset.Changes
ChestXray14Datasetto download the labels and metadata CSV file directly from the NIH Box folder. When I originally implemented this dataset in ChestX-ray14 Dataset and Classification Tasks #392, I couldn't figure out how to download that file from Box automatically, so I mirrored it to my personal Google Drive. This PR fixes that.ChestXray14DatasetAPI docs.ChestXray14Datasetexamples from Jupyter notebooks to Python scripts. I also moved the examples toexamples/cxr/to avoid merge conflicts with Add/cxr comprehensive tutorial and benchmarks for PyHealth paper #773.ChestXray14Datasetunit tests to use thetest-resources/core/chestxray14directory instead of creating and deleting a temporarytestdirectory. This matches the pattern in the unit tests for other datasets. Test images are still generated at test time to avoid adding large files to the repo.PILdeprecation warning (Image.fromarray()will deprecate themodeparameter soon).Testing