ocupy

ocupy copied to clipboard

Ocupy - Oculography Analysis Tools

Ocupy provides functionality for analysis of grouped data:

* Datamat objects for reading of and filtering by group meta-data and data
* Corresponding objects for stimulus data, aligned to Datamat objects
* Measures for prediction quality for eye-tracking data: AUC, NSS, KL, EMD.
* Lower and upper bound calculation for prediction quality of attention models.
* RPC Client/Server for parallel task execution on a grid [deprecated]
* Evaluation (with cross-validation) of attention models 

Install

To install ocupy into your Python environment, type:

python setup.py build
python setup.py test
python setup.py install

The core requirements for ocupy, numpy, scipy and h5py, are automatically installed if not found on your Python path.

If you want to use the parallel module you'll need to install Twisted manually.

Documentation

The documentation is generated by sphinx (http://sphinx.pocoo.org):

cd doc
make html

This will create a set of html files in doc/_build/html. You have to have sphinx and matplotlib installed. Also, ocupy has to be on your path, if you didn't install it add this directory to the python path:

export PYTHONPATH=$PYTHONPATH:`pwd`

Copyright & License

Copyright (C) 2010, 2011, 2012 WhiteMatter Labs GmbH -- http://whitematter.de

Licensed under GPLv2 or later, see file LICENSE in this source tree

Ocupy was developed jointly by WhiteMatter Labs GmbH and the Neurobiopsychology Group at the Unversity of Osnabrueck's Institute of Cognitive Science.

Project Lead: Niklas Wilming [email protected]

Contributors: Robert Muil, Torsten Betz, Hannah Knepper, Johannes Steger, Kilian Klimek