PyMC Tutorial for SciPy 2011
Python
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.
.gitignore
README.rst
SciPy Lecture 1.pdf
SciPy Lecture 4.pdf
bioassay.py
cov.py
mean.py
obs.py
triangular.py
truncated_metropolis.py
weibull.py

README.rst

An Introduction to Bayesian Statistical Modeling using PyMC

PyMC is a Python module that implements Bayesian statistical models and fitting algorithms, including Markov chain Monte Carlo. Its flexibility and extensibility make it applicable to a large suite of problems across all quantitative disciplines. This hands-on tutorial will introduce users to the key components of PyMC and how to employ them to construct, fit and diagnose models. Though some familiarity with statistics is assumed, the tutorial will begin with a brief overview of Bayesian inference, including an introduction to Markov chain Monte Carlo.

Installing PyMC

PyMC is known to run on Mac OS X, Linux and Windows, but in theory should be able to work on just about any platform for which Python, a Fortran compiler and the NumPy module are available. However, installing some extra depencies can greatly improve PyMC's performance and versatility. The following describes the required and optional dependencies and takes you through the installation process.

Dependencies

PyMC requires some prerequisite packages to be present on the system. Fortunately, there are currently only a few dependencies, and all are freely available online.

  • Python version 2.5 or 2.6.
  • NumPy (1.4 or newer): The fundamental scientific programming package, it provides a multidimensional array type and many useful functions for numerical analysis.
  • Matplotlib (optional) : 2D plotting library which produces publication quality figures in a variety of image formats and interactive environments
  • pyTables (optional) : Package for managing hierarchical datasets and designed to efficiently and easily cope with extremely large amounts of data. Requires the HDF5 library.
  • pydot (optional) : Python interface to Graphviz's Dot language, it allows PyMC to create both directed and non-directed graphical representations of models. Requires the Graphviz library.
  • SciPy (optional) : Library of algorithms for mathematics, science and engineering.
  • IPython (optional) : An enhanced interactive Python shell and an architecture for interactive parallel computing.
  • nose (optional) : A test discovery-based unittest extension (required to run the test suite).

There are prebuilt distributions that include all required dependencies. For Mac OS X users, we recommend the MacPython distribution or the Enthought Python Distribution on OS X 10.5 (Leopard) and Python 2.6.1 that ships with OS X 10.6 (Snow Leopard). Windows users should download and install the Enthought Python Distribution. The Enthought Python Distribution comes bundled with these prerequisites. Note that depending on the currency of these distributions, some packages may need to be updated manually.

For Mac OS X 10.6 (Leopard) users, a script for installing all the key dependencies, as well as a recent build of PyMC, can be downloaded from the SciPy Superpack page.

If instead of installing the prebuilt binaries you prefer (or have) to build pymc yourself, make sure you have a Fortran and a C compiler. There are free compilers (gfortran, gcc) available on all platforms. Other compilers have not been tested with PyMC but may work nonetheless.

Compiling the source code

You can check out the latest development source of the code from GitHub repository:

git clone git://github.com/pymc-devs/pymc.git pymc

Then move into the pymc directory and follow the platform specific instructions.

Though this code is technically development source, it contains important bug fixes and features absent from the previous release (2.1) and is relatively stable. Hence, we recommend using the latest development code if possible. A new release is in the works, but will not be complete prior to SciPy 2011.

Windows

One way to compile PyMC on Windows is to install MinGW and MSYS. MinGW is the GNU Compiler Collection (GCC) augmented with Windows specific headers and libraries. MSYS is a POSIX-like console (bash) with UNIX command line tools. Download the Automated MinGW Installer and double-click on it to launch the installation process. You will be asked to select which components are to be installed: make sure the g77 compiler is selected and proceed with the instructions. Then download and install MSYS-1.0.exe, launch it and again follow the on-screen instructions.

Once this is done, launch the MSYS console, change into the PyMC directory and type:

python setup.py install

This will build the C and Fortran extension and copy the libraries and python modules in the C:/Python26/Lib/site-packages/pymc directory.

Mac OS X or Linux

In a terminal, type:

python setup.py config_fc --fcompiler gnu95 build
python setup.py install

The above syntax also assumes that you have gFortran installed and available. The sudo command may be required to install PyMC into the Python site-packages directory if it has restricted privileges.

In addition, the python2.6-dev package may be required to install PyMC on Linux systems. On Ubuntu or Debian, we have had success by installing the following prior to building PyMC:

sudo apt-get install ipython python-setuptools python-dev python-nose
python-tk python-numpy python-matplotlib python-scipy python-networkx
gfortran libatlas-base-dev

Running the test suite

pymc comes with a set of tests that verify that the critical components of the code work as expected. To run these tests, users must have nose installed. The tests are launched from a python shell:

import pymc
pymc.test()

In case of failures, messages detailing the nature of these failures will appear. In case this happens (it shouldn't), please report the problems on the issue tracker specifying the version you are using and the environment.

Code for BDA Project Template

Here is a template for a project to do Bayesian data analysis with PyMC

Code for the Human Development Index vs Total Fertility Rate example

Code to replicate examples from the tutorial.