SPORCO is a Python package for solving optimisation problems with sparsity-inducing regularisation. These consist primarily of sparse coding and dictionary learning problems, including convolutional sparse coding and dictionary learning, but there is also support for other problems such as Total Variation regularisation and Robust PCA. In the current version all of the optimisation algorithms are based on the Alternating Direction Method of Multipliers (ADMM).
The primary requirements are Python itself, and modules numpy, scipy, future, pyfftw, and matplotlib. Module numexpr is not required, but some functions will be faster if it is installed. If module mpldatacursor is installed, function plot.plot will support the data cursor that it provides.
Installation of these requirements is system dependent. Under a recent version of Ubuntu Linux, the following commands should be sufficient for Python 2
sudo apt-get install python-numpy python-scipy python-numexpr sudo apt-get install python-matplotlib python-pip libfftw3-dev sudo pip install future sudo pip install pyfftw
or Python 3
sudo apt-get install python3-numpy python3-scipy python3-numexpr sudo apt-get install python3-matplotlib python3-pip libfftw3-dev sudo pip3 install future sudo pip3 install pyfftw
Some additional dependencies are required for running the unit tests or building the documentation from the package source. Under a recent version of Ubuntu Linux, the following commands should be sufficient for Python 2
sudo apt-get install python-pytest python-numpydoc sudo pip install pytest-runner sudo pip install sphinxcontrib-bibtex
or Python 3
sudo apt-get install python3-pytest python3-numpydoc sudo pip3 install pytest-runner sudo pip3 install sphinxcontrib-bibtex
To install the most recent release of SPORCO from PyPI do
pip install sporco
To install the development version from GitHub do
git clone git://github.com/bwohlberg/sporco.git
followed by
cd sporco python setup.py build python setup.py install
The install command will usually have to be performed with root permissions.
Scripts illustrating usage of the package can be found in the
examples
directory of the source distribution. These examples can
be run from the root directory of the package by, for example
python examples/stdsparse/demo_bpdn.py
To run these scripts prior to installing the package it will be
necessary to first set the PYTHONPATH
environment variable to
include the root directory of the package. For example, in a bash
shell
export PYTHONPATH=$PYTHONPATH:`pwd`
from the root directory of the package.
Jupyter Notebook versions of some of the
demos in examples
are also available in the same directories as
the corresponding demo scripts.
Documentation is available online at Read the Docs, or can be built from the root directory of the source distribution by the command
python setup.py build_sphinx
in which case the HTML documentation can be found in the
build/sphinx/html
directory (the top-level document is
index.html
).
This package is distributed with a BSD license; see the LICENSE
file for details.
Thanks to Aric Hagberg for valuable advice on python packaging, documentation, and related issues.