pypomp
Inference and modeling for partially observed Markov process (POMP) models
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (14.9%) to scientific vocabulary
Repository
Inference and modeling for partially observed Markov process (POMP) models
Basic Info
- Host: GitHub
- Owner: pypomp
- License: mit
- Language: Python
- Default Branch: main
- Homepage: https://pypi.org/project/pypomp/
- Size: 3.19 MB
Statistics
- Stars: 10
- Watchers: 3
- Forks: 3
- Open Issues: 5
- Releases: 0
Metadata Files
README.md
pypomp
Python code for modeling and inference using partially observed Markov process (POMP) models. See the tutorials for user-friendly guides, and the quantitative tests for additional technical examples.
Expected package users
Scientists wanting to perform data analysis on a dynamic system via partially observed Markov processes (POMPs), also called state-space models (SSM) or hidden Markov models (HMM) in other contexts.
- This package design and intended use is similar to the popular pomp R package. As such, many of the expected use cases and motivating examples of this package can be found on the pomp package bibliography page.
Researchers wishing to develop novel inference methodology for POMP models.
- Like the pomp R package, this package provides a framework for implementing computer representations of arbitrary POMP models. This ability provides an environment for researchers to develop, test, and deploy novel algorithms that are applicable to POMP models.
Key features
Estimation, filtering, and inference for highly nonlinear, non-Gaussian state space models via the particle filter.
New algorithms for model-fitting. Gradient descent using a new gradient estimate initialized with a warm-start allows for improved maximum-likelihood inference in even highly challenging epidemiological models, while the gradient estimate can readily be plugged into a sampler from Tensorflow Probability to facilitate more efficient Bayesian inference.
This package leverages JAX for GPU support and just-in-time compilation, enabling a speedup of up to 16x when compared to the pomp R package.
Package Development
The pypomp package is currently at early stages of development. All version numbers below 0.1 are pre-release.
All contributions are welcome! Contributions should keep in mind the intended uses of this package, and its intended users.
The pypomp package is run by the pypomp organization.
Owner
- Name: pypomp
- Login: pypomp
- Kind: organization
- Repositories: 1
- Profile: https://github.com/pypomp
Citation (CITATION.bib)
@software{pypomp2024github,
author = {Aaron Abkemeier and Jun Chen and Edward Ionides and Jesse Wheeler and Kevin Tan},
title = {pypomp},
url = {https://github.com/pypomp/pypomp},
version = {0.1.3},
year = {2024}
}
GitHub Events
Total
- Issues event: 18
- Watch event: 3
- Delete event: 11
- Issue comment event: 5
- Push event: 123
- Pull request review comment event: 35
- Pull request review event: 25
- Pull request event: 8
- Fork event: 4
- Create event: 14
Last Year
- Issues event: 18
- Watch event: 3
- Delete event: 11
- Issue comment event: 5
- Push event: 123
- Pull request review comment event: 35
- Pull request review event: 25
- Pull request event: 8
- Fork event: 4
- Create event: 14
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 15
- Total pull requests: 4
- Average time to close issues: 19 days
- Average time to close pull requests: 18 days
- Total issue authors: 2
- Total pull request authors: 3
- Average comments per issue: 0.0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 15
- Pull requests: 4
- Average time to close issues: 19 days
- Average time to close pull requests: 18 days
- Issue authors: 2
- Pull request authors: 3
- Average comments per issue: 0.0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- AJAbkemeier (14)
- jeswheel (1)
Pull Request Authors
- dannykim0228 (2)
- kunyanghe21 (1)
- junch2002 (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 57 last-month
- Total dependent packages: 0
- Total dependent repositories: 0
- Total versions: 5
- Total maintainers: 2
pypi.org: pypomp
Modeling and inference using partially observed Markov process (POMP) models
- Homepage: https://github.com/pypomp/pypomp
- Documentation: https://pypomp.readthedocs.io/
- License: MIT License
-
Latest release: 0.1.4
published 7 months ago