[jira] [Commented] (MAHOUT-1564) Naive Bayes Classifier for New Text Documents

["Andrew Palumbo (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/MAHOUT-1564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14367278#comment-14367278 ] 

Andrew Palumbo commented on MAHOUT-1564:
----------------------------------------

I may end up splitting this up into two pieces.  Its trivial in the scala mahout, and is almost too abstract a problem to really write a useful job for in MRLegacy- may be more useful as documentation.

> Naive Bayes Classifier for New Text Documents
> ---------------------------------------------
>
>                 Key: MAHOUT-1564
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1564
>             Project: Mahout
>          Issue Type: Improvement
>    Affects Versions: 0.9
>            Reporter: Andrew Palumbo
>            Assignee: Andrew Palumbo
>              Labels: DSL, legacy, scala, spark
>             Fix For: 0.10.1, 0.10.0
>
>
> MapReduce and DSL Naive Bayes implementations currently lack the ability to classify a new document (outside of the training/holdout corpus).  This New feature will do the following.
> 1. Vectorize a new text document using the dictionary and document frequencies from the training/holdout corpus 
>     - assume the original corpus was vectorized using `seq2sparse`; step (1) will use all of the same parameters. 
> 2. Score and label a new document using a previously trained model.
> This effort will need to be done in parallel for MRLegacy and DSL implementations.  Neither should be too much work.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)