PyMC3 is a python module for Bayesian statistical modeling and model fitting which focuses on advanced Markov chain Monte Carlo and variational fitting algorithms. Its flexibility and extensibility make it applicable to a large suite of problems.
Check out the getting started guide!
Features
- Intuitive model specification syntax, for example,
x ~ N(0,1)translates tox = Normal(0,1) - Powerful sampling algorithms, such as the No U-Turn Sampler, allow complex models with thousands of parameters with little specialized knowledge of fitting algorithms.
- Variational inference: ADVI for fast approximate posterior estimation as well as mini-batch ADVI for large data sets.
- Easy optimization for finding the maximum a posteriori (MAP) point
- Relies on Theano which provides:
- Numpy broadcasting and advanced indexing
- Linear algebra operators
- Computation optimization and dynamic C compilation
- Simple extensibility
- Transparent support for missing value imputation
Getting started
- The PyMC3 tutorial or journal publication
- PyMC3 examples and the API reference
- Probabilistic Programming and Bayesian Methods for Hackers
- Bayesian Modelling in Python -- tutorials on Bayesian statistics and PyMC3 as Jupyter Notebooks by Mark Dregan
- Talk at PyData London 2016 on PyMC3
- PyMC3 port of the models presented in the book "Doing Bayesian Data Analysis" by John Kruschke
- Coyle P. (2016) Probabilistic programming and PyMC3. European Scientific Python Conference 2015 (Cambridge, UK)
Installation
The latest release of PyMC3 can be installed from PyPI using pip:
pip install pymc3
Note: Running pip install pymc will install PyMC 2.3, not PyMC3,
from PyPI.
Or via conda-forge:
conda install -c conda-forge pymc3
The current development branch of PyMC3 can be installed from GitHub, also using pip:
pip install git+https://github.com/pymc-devs/pymc3
To ensure the development branch of Theano is installed alongside PyMC3
(recommended), you can install PyMC3 using the requirements.txt
file. This requires cloning the repository to your computer:
git clone https://github.com/pymc-devs/pymc3 cd pymc3 pip install -r requirements.txt
However, if a recent version of Theano has already been installed on your system, you can install PyMC3 directly from GitHub.
Another option is to clone the repository and install PyMC3 using
python setup.py install or python setup.py develop.
Dependencies
PyMC3 is tested on Python 2.7 and 3.5 and depends on Theano, NumPy,
SciPy, Pandas, and Matplotlib (see requirements.txt for version
information).
Optional
In addtion to the above dependencies, the GLM submodule relies on Patsy.
scikits.sparse enables sparse scaling matrices which are useful for large problems.
Citing PyMC3
Salvatier J, Wiecki TV, Fonnesbeck C. (2016) Probabilistic programming in Python using PyMC3. PeerJ Computer Science 2:e55 https://doi.org/10.7717/peerj-cs.55
License
Contributors
See the GitHub contributor page
Sponsors
