Counting 3,541 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Author
Last Commit
Feb. 18, 2019
Created
Jul. 29, 2015

Build Status Coverage Status Code style: black Gitter chat DOI DOI

ArviZ

ArviZ (pronounced "AR-vees") is a Python package for exploratory analysis of Bayesian models. Includes functions for posterior analysis, model checking, comparison and diagnostics.

Documentation

The ArviZ documentation can be found in the official docs. First time users may find the quickstart to be helpful. Additional guidance can be found in the usage documentation.

Installation

Stable

ArviZ is available for installation from PyPI. The latest stable version can be installed using pip:

pip install arviz

Development

The latest development version can be installed from the master branch using pip:

pip install git+git://github.com/arviz-devs/arviz.git

Another option is to clone the repository and install using git and setuptools:

git clone https://github.com/arviz-devs/arviz.git
cd arviz
python setup.py install

Gallery

Ridge plot Parallel plot Trace plot Density plot
Posterior plot Joint plot Posterior predictive plot Pair plot
Energy Plot Violin Plot Forest Plot Autocorrelation Plot

Dependencies

ArviZ is tested on Python 3.5 and 3.6, and depends on NumPy, SciPy, xarray, and Matplotlib.

Citation

If you use ArviZ and want to cite it please use DOI

Here is the citation in BibTeX format

@article{arviz_2019,
	title = {{ArviZ} a unified library for exploratory analysis of {Bayesian} models in {Python}},
	author = {Kumar, Ravin and Colin, Carroll and Hartikainen, Ari and Martin, Osvaldo A.},
	journal = {The Journal of Open Source Software},
	year = {2019},
	doi = {10.21105/joss.01143},
	url = {http://joss.theoj.org/papers/10.21105/joss.01143},
}

Contributions

ArviZ is a community project and welcomes contributions. Additional information can be found in the Contributing Readme

Code of Conduct

ArviZ wishes to maintain a positive community. Additional details can be found in the Code of Conduct

Developing

A typical development workflow is:

  1. Install project requirements: pip install -r requirements.txt
  2. Install additional testing requirements: pip install -r requirements-dev.txt
  3. Write helpful code and tests.
  4. Verify code style: ./scripts/lint.sh
  5. Run test suite: pytest arviz/tests
  6. Make a pull request.

There is also a Dockerfile which helps for isolating build problems and local development.

  1. Install Docker for your operating system
  2. Clone this repo,
  3. Run ./scripts/container.sh --build

This will build a local image with the tag arviz. After building the image tests can be executing by running
docker run arviz bash pytest arviz/tests

An interactive shell can be started by running
docker run -it arviz /bin/bash
The correct conda environment will be activated automatically.

Latest Releases
Beta Release
 Jan. 15 2019
Beta release
 Dec. 18 2018
Beta release
 Dec. 14 2018
Alpha release
 Oct. 3 2018
Preliminary release
 Sep. 21 2018