Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
4 of 13 committers (30.8%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.5%) to scientific vocabulary
Repository
Basic Info
Statistics
- Stars: 563
- Watchers: 55
- Forks: 177
- Open Issues: 46
- Releases: 0
Metadata Files
README.md
⚠️ Warning: this package is not maintained anymore ⚠️
Bayesian inference in HSMMs and HMMs
This is a Python library for approximate unsupervised inference in Bayesian Hidden Markov Models (HMMs) and explicit-duration Hidden semi-Markov Models (HSMMs), focusing on the Bayesian Nonparametric extensions, the HDP-HMM and HDP-HSMM, mostly with weak-limit approximations.
There are also some extensions:
Installing from PyPI
Give this a shot:
bash
pip install pyhsmm
You may need to install a compiler with -std=c++11 support, like gcc-4.7 or higher.
To install manually from the git repo, you'll need cython. Then try this:
bash
python setup.py install
It might also help to look at the travis file to see how to set up a working install from scratch. The last Python version this package has been tested with is Python 3.7.
Running
See the examples directory.
For the Python interpreter to be able to import pyhsmm, you'll need it on your
Python path. Since the current working directory is usually included in the
Python path, you can probably run the examples from the same directory in which
you run the git clone with commands like python pyhsmm/examples/hsmm.py. You
might also want to add pyhsmm to your global Python path (e.g. by copying it to
your site-packages directory).
A Simple Demonstration
Here's how to draw from the HDP-HSMM posterior over HSMMs given a sequence of
observations. (The same example, along with the code to generate the synthetic
data loaded in this example, can be found in examples/basic.py.)
Let's say we have some 2D data in a data.txt file:
bash
$ head -5 data.txt
-3.711962552600095444e-02 1.456401745267922598e-01
7.553818775915704942e-02 2.457422192223903679e-01
-2.465977987699214502e+00 5.537627981813508793e-01
-7.031638516485749779e-01 1.536468304146855757e-01
-9.224669847039665971e-01 3.680035337673161489e-01
In Python, we can plot the data in a 2D plot, collapsing out the time dimension:
```python import numpy as np from matplotlib import pyplot as plt
data = np.loadtxt('data.txt') plt.plot(data[:,0],data[:,1],'kx') ```
We can also make a plot of time versus the first principal component:
python
from pyhsmm.util.plot import pca_project_data
plt.plot(pca_project_data(data,1))
To learn an HSMM, we'll use pyhsmm to create a WeakLimitHDPHSMM instance
using some reasonable hyperparameters. We'll ask this model to infer the number
of states as well, so we'll give it an Nmax parameter:
```python import pyhsmm import pyhsmm.basic.distributions as distributions
obs_dim = 2 Nmax = 25
obshypparams = {'mu0':np.zeros(obsdim), 'sigma0':np.eye(obsdim), 'kappa0':0.3, 'nu0':obsdim+5} durhypparams = {'alpha0':2*30, 'beta_0':2}
obsdistns = [distributions.Gaussian(**obshypparams) for state in range(Nmax)] durdistns = [distributions.PoissonDuration(**durhypparams) for state in range(Nmax)]
posteriormodel = pyhsmm.models.WeakLimitHDPHSMM( alpha=6.,gamma=6., # better to sample over these; see concentration-resampling.py initstateconcentration=6., # pretty inconsequential obsdistns=obsdistns, durdistns=durdistns) ```
(The first two arguments set the "new-table" proportionality constant for the
meta-Chinese Restaurant Process and the other CRPs, respectively, in the HDP
prior on transition matrices. For this example, they really don't matter at
all, but on real data it's much better to infer these parameters, as in
examples/concentration_resampling.py.)
Then, we add the data we want to condition on:
python
posteriormodel.add_data(data,trunc=60)
The trunc parameter is an optional argument that can speed up inference: it
sets a truncation limit on the maximum duration for any state. If you don't
pass in the trunc argument, no truncation is used and all possible state
duration lengths are considered. (pyhsmm has fancier ways to speed up message
passing over durations, but they aren't documented.)
If we had multiple observation sequences to learn from, we could add them to the
model just by calling add_data() for each observation sequence.
Now we run a resampling loop. For each iteration of the loop, all the latent variables of the model will be resampled by Gibbs sampling steps, including the transition matrix, the observation means and covariances, the duration parameters, and the hidden state sequence. We'll also copy some samples so that we can plot them.
python
models = []
for idx in progprint_xrange(150):
posteriormodel.resample_model()
if (idx+1) % 10 == 0:
models.append(copy.deepcopy(posteriormodel))
Now we can plot our saved samples:
python
fig = plt.figure()
for idx, model in enumerate(models):
plt.clf()
model.plot()
plt.gcf().suptitle('HDP-HSMM sampled after %d iterations' % (10*(idx+1)))
plt.savefig('iter_%.3d.png' % (10*(idx+1)))
I generated these data from an HSMM that looked like this:
So the posterior samples look pretty good!
A convenient shortcut to build a list of sampled models is to write
python
model_samples = [model.resample_and_copy() for itr in progprint_xrange(150)]
That will build a list of model objects (each of which can be inspected, plotted, pickled, etc, independently) in a way that won't duplicate data that isn't changed (like the observations or hyperparameter arrays) so that memory usage is minimized. It also minimizes file size if you save samples like
python
import cPickle
with open('sampled_models.pickle','w') as outfile:
cPickle.dump(model_samples,outfile,protocol=-1)
Extending the Code
To add your own observation or duration distributions, implement the interfaces
defined in basic/abstractions.py. To get a flavor of
the style, see pybasicbayes.
References
Matthew J. Johnson. Bayesian Time Series Models and Scalable Inference. MIT PhD Thesis, May 2014.
Matthew J. Johnson and Alan S. Willsky. Bayesian Nonparametric Hidden Semi-Markov Models. Journal of Machine Learning Research (JMLR), 14:673–701, February 2013.
Matthew J. Johnson and Alan S. Willsky, The Hierarchical Dirichlet Process Hidden Semi-Markov Model. 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010), Avalon, California, July 2010.
bibtex
@article{johnson2013hdphsmm,
title={Bayesian Nonparametric Hidden Semi-Markov Models},
author={Johnson, Matthew J. and Willsky, Alan S.},
journal={Journal of Machine Learning Research},
pages={673--701},
volume={14},
month={February},
year={2013},
}
Authors
Matt Johnson, Alex Wiltschko, Yarden Katz, Chia-ying (Jackie) Lee, Scott Linderman, Kevin Squire, Nick Foti.
Owner
- Name: Matthew Johnson
- Login: mattjj
- Kind: user
- Location: San Francisco
- Company: Google
- Website: people.csail.mit.edu/~mattjj
- Repositories: 49
- Profile: https://github.com/mattjj
research scientist @ Google Brain
GitHub Events
Total
- Issues event: 2
- Watch event: 14
- Issue comment event: 3
- Push event: 1
- Pull request review event: 1
- Pull request event: 2
- Fork event: 5
Last Year
- Issues event: 2
- Watch event: 14
- Issue comment event: 3
- Push event: 1
- Pull request review event: 1
- Pull request event: 2
- Fork event: 5
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Matthew Johnson | m****j@c****u | 1,238 |
| Alex Wiltschko | a****w@g****m | 16 |
| Yarden Katz | y****z@g****m | 15 |
| Scott Linderman | s****n@g****m | 12 |
| Jacqueline Lee | c****g@c****u | 6 |
| He-chien Tsai | d****1@g****m | 3 |
| Scott Linderman | s****n@s****u | 3 |
| Kevin Squire | k****e@g****m | 2 |
| Chia-ying | c****g@s****) | 2 |
| allista | a****a@g****m | 1 |
| Dan Stowell | d****l@u****t | 1 |
| Andrea Pierré | 6****l | 1 |
| Adam Novak | a****1@u****u | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 85
- Total pull requests: 19
- Average time to close issues: 19 days
- Average time to close pull requests: 21 days
- Total issue authors: 62
- Total pull request authors: 14
- Average comments per issue: 3.36
- Average comments per pull request: 1.95
- Merged pull requests: 9
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 2
- Pull requests: 2
- Average time to close issues: 1 day
- Average time to close pull requests: 1 day
- Issue authors: 2
- Pull request authors: 1
- Average comments per issue: 2.0
- Average comments per pull request: 0.0
- Merged pull requests: 2
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- mattjj (6)
- jmgo (5)
- gxhrid (5)
- yarden (4)
- manasa001 (2)
- mathDR (2)
- nfoti (2)
- AnuragDataGeek (2)
- tansey (2)
- Krozard (2)
- alexbw (2)
- falakmasir (1)
- FancyBrush (1)
- dchouren (1)
- Wusir2018 (1)
Pull Request Authors
- yarden (3)
- kir0ul (2)
- bacalfa (2)
- ghost (2)
- tdhopper (1)
- mmargenot (1)
- NickHoernle (1)
- audiracmichelle (1)
- ameya98 (1)
- danstowell (1)
- interfect (1)
- TrellixVulnTeam (1)
- slinderman (1)
- allista (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 226 last-month
- Total dependent packages: 0
- Total dependent repositories: 10
- Total versions: 8
- Total maintainers: 1
pypi.org: pyhsmm
Bayesian inference in HSMMs and HMMs
- Homepage: https://github.com/mattjj/pyhsmm
- Documentation: https://pyhsmm.readthedocs.io/
- License: MIT
-
Latest release: 0.1.7
published about 9 years ago
Rankings
Maintainers (1)
Dependencies
- numpy *