fixationmodel 0.1.0

A least-squares offline method to test if tracked gaze points resemble a fixation

A least-squares offline method to test if tracked gaze points resemble a fixation.

Install

With pip:

$ pip install fixationmodel

Usage

The data structure pointlist is used thoroughly. It is a list of points, where each point is a list [x, y].

The usage is simple:

>>> import fixationmodel
>>> rawdata = [
    [130.012, 404.231],
    [129.234, 403.478],
    [None, None],
    [133.983, 450.044],
    ...
]
>>> results = fixationmodel.fit(rawdata)
>>> print(results)
{
    'centroid': [344.682, 200.115],
    'mean_squared_error': 0.000166802
}

API

fixationmodel.fit(gazepointlist)

Parameter:

• gazepointlist: a list of [x, y] points i.e. a list of lists.

Return dict with following keys:

• centroid: a list [x, y], the most probable target of the fixation

• mean_squared_error: the average squared error for a point.

fixationmodel.version

For developers

Use virtualenv:

$ virtualenv -p python3.5 fixationmodel-py
$ cd fixationmodel-py
$ source bin/activate
...
$ deactivate

Testing

Follow instructions to install pyenv and then either run quick tests:

$ python3.5 setup.py test

or comprehensive tests for multiple Python versions in tox.ini:

$ pyenv local 2.6.9 2.7.10 3.2.6 3.3.6 3.4.3 3.5.0
$ eval "$(pyenv init -)"
$ pyenv rehash
$ tox

Versioning

Semantic Versioning 2.0.0

License

MIT License