implementing naive bayes classifier using nltk

[shanki himanshu]

the formula for naive bayes is

P(A/B1,B2,B3...Bn) =

[ P(A) * P(B1/A) * P(B2/A) * . . . P(Bn/A) ] / [ P(B1) * P(B2) *....P(Bn) ]

i am working on a project to classify email as spam or not. i have a large data set.
i am using nltk package in python.
my question is how to find the probabilities of the right side of the expression.
and after that how should i set my threshold value?

[TrustyTony]

You did read http://nltk.googlecode.com/svn/trunk/doc/book/ch06.html , didn't you?

[shanki himanshu]

thanks for the link. i have read it.
now i want to know is there any advantage of coding naive bayes in python rather than any other language like c++?