Unsupervised and Semi-supervised Dirichlet Process Heterogeneous Mixtures
Project description
Implements Dirichlet Process Heterogeneous Mixtures of exponential family distributions for clustering heterogeneous data without choosing the number of clusters. Inference can be performed with Gibbs sampling or coordinate ascent mean-field variational inference. For semi-supervised learning, Gibbs sampling supports must-link and cannot-link constraints. A novel variational inference algorithm was derived to handle must-link constraints.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
| Filename, size | File type | Python version | Upload date | Hashes |
|---|---|---|---|---|
| Filename, size dphmix-0.2.0.tar.gz (15.5 kB) | File type Source | Python version None | Upload date | Hashes View |
