fastTopics
swMATH39042CRANfastTopicsMaRDI QIDQ54742
Fast Algorithms for Fitting Topic Models and Non-Negative Matrix Factorizations to Count Data
Kushal Dey, Peter Carbonetto, Kevin Luo, Matthew Stephens
Last update: 15 January 2024
Copyright license: 2-clause BSD License, File License
Software version identifier: 0.6-142, 0.6-135, 0.6-163
Source code repository: https://github.com/stephenslab/fastTopics
Implements fast, scalable optimization algorithms for fitting topic models ("grade of membership" models) and non-negative matrix factorizations to count data. The methods exploit the special relationship between the multinomial topic model (also, "probabilistic latent semantic indexing") and Poisson non-negative matrix factorization. The package provides tools to compare, annotate and visualize model fits, including functions to efficiently create "structure plots" and identify key features in topics. The 'fastTopics' package is a successor to the 'CountClust' package. Note that the 'fastTopicis' package on GitHub has more vignettes illustrating application to single-cell RNA-seq data.
Related Items (1)
This page was built for software: fastTopics
