[Conformal EEG] TUEV Dataset and Task #752
Open
+981
−402
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
jhnwu3
requested changes
Dec 24, 2025
Collaborator
jhnwu3
left a comment
jhnwu3
left a comment
There was a problem hiding this comment.
Sorry for the late review, so close. I am very excited to send this to Jathurshan for testing.
I think what'll be really cool is testing if our parallel processing approach can speed up development haha.
| dataset_name: name of the dataset. | ||
| root: root directory of the raw data. *You can choose to use the path to Cassette portion or the Telemetry portion.* | ||
| dataset_name: name of the dataset. | ||
| config_path: Optional configuration file name, defaults to "tuev.yaml". |
Collaborator
There was a problem hiding this comment.
It sounds silly, but can we add some of the example code in the docstrings here (i.e how a user would quickly initialize and use it)? And maybe a pointer to the notebook that people would refer to here if they wanted to use it.
jhnwu3
requested changes
Dec 24, 2025
|
|
||
| signals, times, rec, raw = self.readEDF(edf_path) | ||
| signals = self.convert_signals(signals, raw) | ||
| feats, offending_channels, labels = self.BuildEvents(signals, times, rec) |
Collaborator
There was a problem hiding this comment.
By any chance, can we split the label processing into something separate from the signal processing?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Contributor: Sayeed Sajjad Razin (razin93937@gmail.com)
Contribution Type: Update Dataset, Task, Example
Description
This PR introduces support for the TUEV (TUH EEG Events) dataset in PyHealth 2.0, including a new EEGEventsTUEV task for EEG event classification and a quickstart notebook demonstrating dataset loading and model training.
Files to review
Files to review
pyhealth/datasets/configs/tuev.yaml- New configuration file for TUEV dataset structurepyhealth/datasets/tuev.py- Updated TUEVDataset class with metadata preparation and default task propertypyhealth/task/__init__.py- Added import for EEGEventsTUEV taskpyhealth/task/temple_university_EEG_tasks.py- Added EEGEventsTUEV class for multi-class EEG event detectionexamples/conformal_eeg/tuev_eeg_quickstart.ipynb- New Jupyter notebook with end-to-end example for loading TUEV data, setting tasks, and training a simple CNN classifiertests/core/test_tuev.py- Added unit tests for the TUEV dataset and accompanying task.