Hi Rahul, We plan to add online model updates with Spark Streaming, perhaps in v1.1, starting with linear methods. Please open a JIRA for Naive Bayes. For Naive Bayes, we need to update the priors and conditional probabilities, which means we should also remember the number of observations for the updates.
Best, Xiangrui On Tue, Jul 8, 2014 at 7:35 AM, Rahul Bhojwani <rahulbhojwani2...@gmail.com> wrote: > Hi, > > I am using the MLlib Naive Bayes for a text classification problem. I have > very less amount of training data. And then the data will be coming > continuously and I need to classify it as either A or B. I am training the > MLlib Naive Bayes model using the training data but next time when data > comes, I want to predict its class and then incorporate that also in the > model for next time prediction of new data(I think that is obvious). > > So I am not able to figure out what is the way to do that using MLlib Naive > Bayes. Is it that I have to train the model on the whole data every time new > data comes in?? > > Thanks in Advance! > -- > Rahul K Bhojwani > 3rd Year B.Tech > Computer Science and Engineering > National Institute of Technology, Karnataka
