Metadata-Version: 2.1
Name: numcertainties
Version: 0.0.0
Summary: uncertainty quantification for numerical computations
Home-page: https://github.com/APN-Pucky/numcertainties
Author: APN
Author-email: APN-Pucky@no-reply.github.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Provides-Extra: dev
Provides-Extra: docs
License-File: LICENSE

# numcertainties

This project aims to unify the use of several error propagation libraries in python:

- <https://github.com/HDembinski/jacobi>
- <https://github.com/lebigot/uncertainties/>
- <https://github.com/tisimst/mcerp>
- (<https://github.com/tisimst/soerp>)

In future general differentiation routines could be used to get the jacobian similar to the `jacobi` package to get uncertainties from there:

- <https://pypi.org/project/numdifftools/>
- scipy
- (sympy for analytic derivatives i.e. as we store the operations we can do an anlytic derivative?, though eg. exp will be difficult)

TODO:
- p values / confidence
- handle mixed types of uncertainties
