I have looked around for information about this but I still feel unsure about whether this is possible. I have recently developed a naive bayes model in sci-kit learn that takes some short text data (along with a few other categorical features) and develops a classifier model. I would like to ultimately deploy this classifier in our Java based app.
I am thinking of using Mahout to build the model, especially given the fact that we have a Hadoop cluster and it would be good to train the model there and then be able to serialize it there then migrate it to our Java App environment. I wanted to know if this is possible and what would I ultimately need to do in order to get it to work. In the Mahout in Action book it says that Naive Bayes only works for "text-like" variables, do that mean you cannot combine categorical variables with text variables? Thanks, Chirag
