NIMFA: A Python Library for Nonnegative Matrix Factorization

TL;DR

NIMFA is an open-source Python library that offers a comprehensive, flexible, and user-friendly platform for applying, comparing, and developing nonnegative matrix factorization algorithms with support for various data formats.

Contribution

It introduces a modular, hierarchical design for NMF in Python, integrating multiple algorithms, initialization methods, and quality metrics in a unified interface.

Findings

Supports both dense and sparse matrices

Includes state-of-the-art NMF algorithms and initialization methods

Facilitates development of new NMF strategies

Abstract

NIMFA is an open-source Python library that provides a unified interface to nonnegative matrix factorization algorithms. It includes implementations of state-of-the-art factorization methods, initialization approaches, and quality scoring. It supports both dense and sparse matrix representation. NIMFA's component-based implementation and hierarchical design should help the users to employ already implemented techniques or design and code new strategies for matrix factorization tasks.