Friendly modelling API

PyMC allows you to write down models using an intuitive syntax to describe a data generating process.

Cutting edge algorithms and model building blocks

Fit your model using gradient-based MCMC algorithms like NUTS, using ADVI for fast approximate inference — including minibatch-ADVI for scaling to large datasets — or using Gaussian processes to build Bayesian nonparametric models.

import pymc as pm

X = np.random.normal(size=100)
y = np.random.normal(X) * 1.2

with pm.Model() as linear_model:
    weights = pm.Normal("weights", mu=0, sigma=1)
    noise = pm.Gamma("noise", alpha=2, beta=1)
    y_observed = pm.Normal(
        "y_observed",
        mu=X @ weights,
        sigma=noise,
        observed=y,
    )

    prior = pm.sample_prior_predictive()
    posterior = pm.sample()
    posterior_pred = pm.sample_posterior_predictive(posterior)

Installation

Via conda-forge:

conda install -c conda-forge pymc

Latest (unstable):

pip install git+https://github.com/pymc-devs/pymc

License

PyMC is licensed under the Apache License, V2.

Citing PyMC

Please choose from the following:

  • DOIpaper Probabilistic programming in Python using PyMC3, Salvatier J., Wiecki T.V., Fonnesbeck C. (2016)
  • DOIzenodo A DOI for all versions.
  • DOIs for specific versions are shown on Zenodo and under Releases

See Google Scholar for a continuously updated list of papers citing PyMC.

Support and sponsors

PyMC is a non-profit project under NumFOCUS umbrella. If you value PyMC and want to support its development, consider donating to the project or read our support PyMC page.