wpca: Weighted Principal Component Analysis in Python

Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 2188
Joined: Thu May 08, 2014 5:37 am

wpca: Weighted Principal Component Analysis in Python

Post by Ada Coda » Fri Dec 31, 2021 3:59 am

wpca: Weighted Principal Component Analysis in Python

Abstract: wpca, written in Python, offers several implementations of Weighted Principal Component Analysis and uses an interface similar to scikit-learn's sklearn.decomposition.PCA. Implementations include a direct decomposition of a weighted covariance matrix to compute principal vectors, and then a weighted least squares optimization to compute principal components, and an iterative expectation-maximization approach to solve simultaneously for the principal vectors and principal components of weighted data. It also includes a standard non-weighted PCA implemented using the singular value decomposition, primarily to be useful for testing.

Credit: VanderPlas, Jake

Site: https://github.com/jakevdp/wpca
https://ui.adsabs.harvard.edu/abs/2021A%26A...653A..43C

Bibcode: 2021ascl.soft12023V

ID: ascl:2112.023

Post Reply