Skip to content

ACL injury prediction with classical machine learning techniques (primarily addressing the extreme class imbalance).

Notifications You must be signed in to change notification settings

We-Gold/wpi-acl-injury-risk

Repository files navigation

WPI DS 502 Project

This is the codebase for our final project in DS 502 (Fall 2025).

Our goal is to preemptively predict ACL injury for college athletes.

We are using the following dataset: https://www.kaggle.com/datasets/ziya07/athlete-injury-and-performance-dataset/data

Final Documents

See our final presentation here: https://docs.google.com/presentation/d/1lFzJDqKgKhq0uyFfrejo3gL4j6Si64Tk/edit?usp=sharing&ouid=112144393606313004477&rtpof=true&sd=true

See our final report: Final Report

Team

  • Bryan Drozda
  • Weaver Goldman
  • Hongchao Hu
  • Ava Laughlin
  • Gage Nagy

Usage

We are using uv for managing the Python project.

  1. Install uv: https://docs.astral.sh/uv/getting-started/installation/

From inside this folder:

  1. If you don't already have Python 3.12, use uv python install 3.12

  2. Build venv (installs packages): uv sync

To add a package, use uv add <package-name>. DO NOT pip install it!

To activate the environment in VSCode, follow these instructions: astral-sh/uv#9637

Note: I've tried to add a bunch of common packages already. You can see which ones in pyproject.toml

Usage with Python Scripts

Use uv run python src/acl-injury/main.py, or something equivalent for a different script.

To save the output, use uv run src/acl-injury/main.py > out.txt

Usage with Jupyter Notebooks

I recommend using notebooks through VSCode. With this, you can easily write Python scripts and Jupyter notebooks in the same application.

To activate the environment in VSCode, follow these instructions: astral-sh/uv#9637

About

ACL injury prediction with classical machine learning techniques (primarily addressing the extreme class imbalance).

Topics

Resources

Stars

Watchers

Forks

Contributors 3

  •  
  •  
  •