mc3: Multi-Core Markov-Chain Monte Carlo¶
|Author:||Patricio Cubillos and collaborators (see Collaborators)|
|Organizations:||Space Research Institute (IWF)|
|Date:||Jan 20, 2022|
mc3 got an extreme make over! (version 3.0+) and now follows the current best practices for Python development. The package changed name from
mc3, it is now pip-installable (
pip install mc3), it added support for nested sampling, and is extensively tested with pytest and travis.
mc3 is a Bayesian-statistics tool that offers:
- Levenberg-Marquardt least-squares optimization.
- Markov-chain Monte Carlo (MCMC) posterior-distribution sampling following the:
- Metropolis-Hastings algorithm with Gaussian proposal distribution,
- Differential-Evolution MCMC (DEMC), or
- DEMCzs (Snooker).
- Nested-sampling via dynesty.
The following features are available when running
- Execution from the Shell prompt or interactively through the Python interpreter.
- Single- or multiple-CPU parallel computing.
- Uniform non-informative, Jeffreys non-informative, or Gaussian-informative priors.
- Gelman-Rubin convergence test.
- Share the same value among multiple parameters.
- Fix the value of parameters to constant values.
- Correlated-noise estimation with the Time-averaging or the Wavelet-based Likelihood estimation methods.
mc3 is compatible with Python3.6+.
(There is support for Python2.7 up to
mc3 version 3.0.1).
All of these people have made a direct or indirect contribution to
mc3, and in many instances have been fundamental in the
development of this package.
- Getting Started
- MCMC Tutorial
- Argument Inputs
- Input Data
- Modeling Function
- Fitting Parameters
- Parameters Stepping Behavior
- Parameter Priors
- Parameter Names
- Sampler Algorithm
- MCMC Configuration
- Wavelet-Likelihood MCMC
- MCMC Run
- Resume a Previous Run
- Inputs from Files
- Nested Sampling Tutorial
- Optimization Tutorial
- Time Averaging
- Please cite this paper if you found
mc3useful for your research:
- Cubillos et al. (2017): On the Correlated-noise Analyses Applied to Exoplanet Light Curves, AJ, 153, 3.
We welcome your feedback or inquiries, please refer them to:
Patricio Cubillos (patricio.cubillos[at]oeaw.ac.at)
mc3 is open-source open-development software under the MIT
Thank you for using