Skip to content

Conversation

@midquan
Copy link

@midquan midquan commented Sep 30, 2025

Authors:

Michael Quan (mdquan2)

Daniel Trugubenko (dvt3)

Contribution Type:

Dataset

Link to Original Paper:

https://arxiv.org/abs/2405.16395

Description:
This pull request adds a PyHealth-compatible loader for the UCI Daily and Sports Activities dataset. The class parses raw sensor data into the patient-visit structure and supports activity recognition tasks. The dataset includes 19 activities performed by 8 subjects, with 45 sensor channels per sample. All code is documented and follows PyHealth’s dataset standards.

Files to test/review:

pyhealth/datasets/daily_sports_activities.py (new dataset loader)
pyhealth/unitests/test_datasets/test_daily_sports.py (new dataset loader test)

@midquan
Copy link
Author

midquan commented Sep 30, 2025

I'm not sure how to add labels, but please let me know what and which ones to add? Do I need to do it on the CLI?

Copy link
Collaborator

@jhnwu3 jhnwu3 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hey, happy to see this is still alive. Some quick thoughts:

  • Can you move your sports_activity.py dataset file into datasets/ ?
  • Can you add a configs/sports_activity.yaml file to configs/ ? If you need an example, please see this tutorial on datasets https://colab.research.google.com/drive/1voSx7wEfzXfEf2sIfW6b-8p1KqMyuWxK?usp=sharing
  • All unit tests have moved into tests/core
  • Please double check that your test case runs in under 20 seconds, because it's really expensive to integrate unit tests that are heavy.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants