Skip to content

A repository for example codes to do Gaussian Process regression

Notifications You must be signed in to change notification settings

julianakwan/emulator-examples

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Example codes for emulation

A repository for example codes to do Gaussian Process regression - these are all under development!

emceegp.py uses the procedure detailed in Heitmann et al. (2009) to build emulators. It will determine the PCA basis and then use MCMC to fit for the hyperparameters using emcee . Because of this, you will need to have emcee installed as well. It does not make predictions - you will need to take the predicted weights and PC basis functions plug them into a separate code.

multires_gp.py uses heteroschedastic GP regression (using GPy ) to weight power spectra from different resolution simulations and combine them under one single GP.

Please get in touch: julianakwan123@gmail.com if you have questions!

About

A repository for example codes to do Gaussian Process regression

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages