• License: Apache-2.0
• Home: https://github.com/AmpersandTV/pymc3-hmm
• Development: https://github.com/AmpersandTV/pymc3-hmm
• Documentation: https://nbviewer.jupyter.org/github/AmpersandTV/pymc3-hmm/tree/main/examples/
• 24798 total downloads
• Last upload: 2 years and 7 months ago

Description

Fully implemented PyMC3 Distribution classes for HMM state sequences (DiscreteMarkovChain) and mixtures that are driven by them (SwitchingProcess). A forward-filtering backward-sampling (FFBS) implementation (FFBSStep) that works with NUTS—or any other PyMC3 sampler. A conjugate Dirichlet transition matrix sampler (TransMatConjugateStep). Support for time-varying transition matrices in the FFBS sampler and all the relevant Distribution classes.