Numerical tool for performing uncertainty quantification

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for jonathf from gravatar.com jonathf

Unverified details

These details have not been verified by PyPI
Meta
  • License: MIT License (MIT license)
  • Requires: Python >=3.7
  • Provides-Extra: dev
Classifiers

Project description

https://github.com/jonathf/chaospy/raw/master/docs/_static/chaospy_logo.svg

circleci codecov readthedocs downloads pypi

Chaospy is a numerical toolbox designed for performing uncertainty quantification through polynomial chaos expansions and advanced Monte Carlo methods implemented in Python. It includes a comprehensive suite of tools for low-discrepancy sampling, quadrature creation, polynomial manipulations, and much more.

The philosophy behind chaospy is not to serve as a single solution for all uncertainty quantification challenges, but rather to provide specific tools that empower users to solve problems themselves. This approach accommodates well-established problems but also serves as a foundry for experimenting with new, emerging problems. Emphasis is placed on the following:

  • Focus on an easy-to-use interface that embraces the pythonic code style <https://docs.python-guide.org/writing/style/>.

  • Ensure the code is “composable,” meaning it’s designed so that users can easily and effectively modify parts of the code with their own solutions.

  • Strive to support a broad range of methods for uncertainty quantification where it makes sense to use chaospy.

  • Ensure that chaospy integrates well with a wide array of other projects, including numpy <https://numpy.org/>, scipy <https://scipy.org/>, scikit-learn <https://scikit-learn.org>, statsmodels <https://statsmodels.org/>, openturns <https://openturns.org/>, and gstools <https://geostat-framework.org/>, among others.

  • Contribute all code as open source to the community.

Installation

Installation is straightforward via pip:

pip install chaospy

Alternatively, if you prefer Conda:

conda install -c conda-forge chaospy

After installation, visit the documentation to learn how to use the toolbox.

Development

To install chaospy and its dependencies in developer mode:

pip install -e .[dev]

Testing

To run tests on your local system:

pytest --doctest-modules chaospy/ tests/ README.rst

Documentation

Ensure that pandoc is installed and available in your path to build the documentation.

From the docs/ directory, build the documentation locally using:

cd docs/
make html

Run make without arguments to view other build targets. The HTML documentation will be output to doc/.build/html.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page