PyMVPA is a Python module intended to ease pattern classification analyzes of large datasets. PyMVPA provides high-level abstraction of typical processing steps and a number of implementations of some popular algorithms.

While it is not limited to the neuroimaging domain, it is eminently suited for such datasets. PyMVPA is truely free software (in every respect) and additionally requires nothing but free-software to run.

PyMVPA stands for MultiVariate Pattern Analysis (MVPA) in Python.

What's New in This Release: [ read full changelog ]

· ProcrusteanMapper with orthogonal and oblique transformations.
· Ability to generate simple reports using reportlab. See/run examples/match_distribution.py for example.
· TreeClassifier – construct simple hierarchies of classifiers.
· wtf() to report information about the system/PyMVPA to be included in the bug reports.
· Parameter ‘reverse’ to swap training/testing splits in Splitter .
· Example code for the analysis of event-related dataset using ERNiftiDataset.
· toEvents() to create lists of Event.
· mvpa-prep-fmri was extended with plotting of motion correction parameters.
· ColumnData can be explicitly told either file contains a header.
· In XMLBasedAtlas (e.g. fsl atlases) it is now possible to provide custom ‘image_file’ to get maps or indexes for the areas given an atlas’s volume registered into subject space.
· Updated included LIBSVM version to 2.89 and provided support for its “silencing”.