hlda

Gibbs sampler for the Hierarchical Latent Dirichlet Allocation topic model. This is based on the hLDA implementation from Mallet, having a fixed depth on the nCRP tree. The output looks buggy, DO NOT USE YET!!

• hlda.py is the Gibbs sampler.
• a notebook to test with synthetic data can be found in the notebooks folder.

• The Nested Chinese Restaurant Process and Bayesian Nonparametric Inference of Topic Hierarchies
• Hierarchical Topic Models and the Nested Chinese Restaurant Process