/pyquic

Python wrapper for QUIC

Primary LanguageC

Summary

A python wrapper for QUIC, computing a sparse inverse covariance matrix estimation using quadratic approximation. It is based on Version 1.2 of the QUIC code. The wrapper was successfully tested on OSX (10.6), Ubuntu (11.04) and Arch Linux.

The modifications to the original C++ source (from the above website) are minimal: See the diff for the second overall commit.

Requirements

Building

In the directorypy_quic/, run make. Make sure that your lapack library is available. If necessary, add library_dirs in py_quic/setup.py.

Testing

For testing the algorithm, run python test.py after a successful build. Note that the file ER_692.mat has to be in the main directory. It is contained in the MEX package archive from the QUIC.

More Information

See Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation by Cho-Jui Hsieh, Mátyás A. Sustik, Inderjit S. Dhillon, Pradeep Ravikumar, available on the QUIC website.