drahnr / bayes-glib Goto Github PK

------------------------------------------------------------------------------
                Bayes-GLib - Bayesian Classification for GLib
------------------------------------------------------------------------------

This is a simple attempt at making a classifier that can be used to train and
learn about data used within a given domain. It exists mostly so that I can
learn how to write a Bayesian classifier. Alternatively, it might prove useful
to be able to use the same classification API from multiple languages through
the GObject Introspection.

Bits and pieces of this are based on the reverend.thomas python module. It,
too, is licensed under the LGPL (2.1) by Amir Bakhtiar.

I make no guarantees about maintaining this code.

-- Christian


------------------------------------------------------------------------------
Examples
------------------------------------------------------------------------------

Python example

>>> from gi.repository import Bayes
>>> c = Bayes.Classifier()
>>> c.train('french', 'le la les du un une je il elle de en')
>>> c.train('german', 'der die das ein eine')
>>> c.train('spanish', 'el uno una las de la en')
>>> c.train('english', 'the it she he they them are were to')
>>> for g in c.guess('they were flying planes'):
...     print '%12s: %0.4f' % (g.get_name(), g.get_probability())
...
     english: 0.4975
     spanish: 0.0000
      french: 0.0000
      german: 0.0000