Skip to content

linatnguyen/USA-Rugby-Load-vs.-Athlete-Availability

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 

Repository files navigation

USA-Rugby-Load-vs.-Athlete-Availability

Project Objective

The main purpose of this project is to perform machine learning regression to predict the percent of available athletes based on the amount of load they are given. The goal is to help optimize fitness, while also trying to minimize injuries to improve overall team and individual performance for the USA Rugby Women's 7s team.

Methods Used

Data Mining Predictive Modeling Data Manipulation Machine Learning Regression Data Visualization

Technologies

Python 3

Project Description

Data is provided by USA Rugby Women's 7s, and includes athlete availability, daily wellness, and Statsports GPS data. We want to see if players are becomming more fit overtime as the season progresses, or if more injuries are occuring. Some challenges with this project is as follows:

  1. Incomplete dataset
  2. All athletes are different, so there are a lot of factors that play into determining how much load they can handle
  3. Important load features are sport specific - in this case, field sports generally take running load into account
  4. Data is only collected from the 2021-2022 season

Models Tested

  • Support Vector Regressor
  • Random Forest Regressor
  • Gradient Boosting Regressor
  • Decision Tree Regressor
  • Linear Regression

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published