Pattern Classification Frameworks?

[Evan Klitzke]

Hi all,

What frameworks are there available for doing pattern classification?
I'm generally interested in the problem of mapping some sort of input
to one or more categories. For example, I want to be able to solve
problems like taking text and applying one or more tags to it like
"romance", "horror", "poetry", etc. This isn't really my research
specialty, but my understanding is that Bayesian classifiers are
generally used for problems like this. I've had CRM114 recommended to
me, but as far as I can tell there aren't any python bindings for
this. From a few searches online, I've come across the Open Bayes
project which is a Python library for working with Bayesian networks,
and it also appears that DSPAM has some Python bindings, but from the
cursory look I gave it it's hard to tell how general purpose the DSPAM
engine is. Has anyone worked with any of these frameworks? Are there
any other frameworks I should be aware of?

Also, as a sidenote, are there any texts that anyone can recommend to
me for learning more about this area? I'm a mathematician by training,
so I'm not afraid to jump into reasonably advanced statistics
papers/books if necessary.

-- 
Evan Klitzke <evan at yelp.com>