dfm/emcee

The Python ensemble sampling toolkit for affine-invariant MCMC

What it solves

It provides a stable, well-tested Python implementation of the affine-invariant ensemble sampler for Markov chain Monte Carlo (MCMC) simulations, which are used to estimate the parameters of a mathematical model based on observed data.

How it works

The toolkit implements the specific ensemble sampling algorithm proposed by Goodman & Weare (2010), which allows the sampler to efficiently explore the parameter space without needing to manually tune the proposal distribution.

Who it’s for

Researchers, particularly in fields like astrophysics, who need a robust tool for Bayesian parameter estimation and sampling from complex probability distributions.

Highlights

  • Affine-invariant ensemble sampling
  • Open source and widely used in published astrophysics research
  • MIT License

Related

  • Project
    pymc-devs/pymc

    PyMC is a Python package for Bayesian statistical modeling that uses MCMC and variational inference algorithms to estimate parameters in complex probabilistic models.

  • Project
    scikit-learn-contrib/MAPIE

    MAPIE is a Python library that provides model‑agnostic prediction intervals and risk‑controlled prediction sets for regression, classification, time‑series, and computer‑vision tasks. It works with any scikit‑learn estimator (and can wrap TensorFlow/PyTorch models) and offers statistically guaranteed uncertainty estimates based on conformal prediction. Install via `pip install mapie` and use the `MapieRegressor` or `MapieClassifier` wrappers to obtain calibrated intervals/sets with minimal code.

  • Project
    joshspeagle/dynesty

    A pure Python package for computing Bayesian posteriors and evidences using Dynamic Nested Sampling.

  • Project
    sbi-dev/sbi

    A Python package for simulation-based inference that estimates the posterior distribution of simulator parameters based on observed data using neural networks.

  • Project
    python-adaptive/adaptive

    A Python library for parallel active learning of mathematical functions that intelligently selects the best points to sample in a parameter space to reduce computational cost.