ASCL.net

Astrophysics Source Code Library

Making codes discoverable since 1999

ASCL Code Record

[ascl:1611.013] pyGMMis: Mixtures-of-Gaussians density estimation method

pyGMMis is a mixtures-of-Gaussians density estimation method that accounts for arbitrary incompleteness in the process that creates the samples as long as the incompleteness is known over the entire feature space and does not depend on the sample density (missing at random). pyGMMis uses the Expectation-Maximization procedure and generates its best guess of the unobserved samples on the fly. It can also incorporate an uniform "background" distribution as well as independent multivariate normal measurement errors for each of the observed samples, and then recovers an estimate of the error-free distribution from which both observed and unobserved samples are drawn. The code automatically segments the data into localized neighborhoods, and is capable of performing density estimation with millions of samples and thousands of model components on machines with sufficient memory.

Code site:
https://github.com/pmelchior/pyGMMis
Appears in:
http://adsabs.harvard.edu/abs/2016arXiv161105806M
Bibcode:
2016ascl.soft11013M

ascl:1611.013
Add this shield to your page
Copy the above HTML to add this shield to your code's website.
Views: 703