Skip to content

Cross-validate regression models featuring Ridge and LASSO regularizations to predict coral reef biodiversity

License

Notifications You must be signed in to change notification settings

mingkaid/2016-summer-jordan-coral-reef-regression

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Benchmarking Jordanian Coral-Reef Fish Biodiversity with Reef Physical Properties and Biotic Factors

Capstone project for 2016 Summer Ecosystem Experience for Undergraduates (SEE-U) in Jordan

Contents:

  • Cross-validated Ridge and lasso regression models that predict indicators of coral-reef-fish biodiversity using data from Wagner et al. (https://peerj.com/articles/1459/)
  • Cross-validated the models on my own field-collected data
  • Visualized model performance under different lambda values (strengths) of different regularization terms

Point of Improvement: For the field-collected data, I was unable to create a validation set to optimize hyperparameters using out-of-sample data, due to the very low sample size (N=5)

Directed by

  • Professor Jenna Mara Lawrence of Columbia University and
  • Doctor Suzanne Macey of American Museum of Natural History

Courtesy of Jordan Marine Science Station

About

Cross-validate regression models featuring Ridge and LASSO regularizations to predict coral reef biodiversity

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published