2020leon/rpca

Python implementation of robust principal component analysis

RPCA

Robust principal component analysis (robust PCA, RPCA) is a modification of principal component analysis (PCA) which works well with respect to grossly corrupted observations. The package implements robust PCA in exact alternating Lagrangian multipliers (EALM) algorithm and inexact alternating Lagrangian multipliers (IALM) algorithm. The implementation refers the paper and its MATLAB implementation.

Installation

Use the package manager pip to install.

pip install git+https://github.com/2020leon/rpca.git

Usage

import numpy as np
import rpca.ealm
import rpca.ialm


D = np.random.rand(20, 20)
A0, E0 = rpca.ealm.fit(D)
A1, E1 = rpca.ialm.fit(D)

Contributing

Contributing is welcome!

License

MIT

References

• Robust principal component analysis - Wikipedia
• Lin, Zhouchen, Minming Chen, and Yi Ma. "The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices."
• Sample code