[jira] [Comment Edited] (SPARK-7014) Support loading VW formatted data.

["Ram Sriharsha (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-7014?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14503476#comment-14503476 ] 

Ram Sriharsha edited comment on SPARK-7014 at 4/20/15 7:36 PM:
---------------------------------------------------------------

good point, the priority is minor.
the plan is to have it as a separate library code like spark-avro for example.
it would be good to know who else is using VW formatted data for example., maybe there isn't enough usage to warrant a parser.


was (Author: rams):
good point, the priority is minor.
the plan is to have it as a separate library code like spark-afro for example.
it would be good to know who else is using VW formatted data for example., maybe there isn't enough usage to warrant a parser.

> Support loading VW formatted data.
> ----------------------------------
>
>                 Key: SPARK-7014
>                 URL: https://issues.apache.org/jira/browse/SPARK-7014
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib
>            Reporter: Ram Sriharsha
>            Assignee: Ram Sriharsha
>            Priority: Minor
>   Original Estimate: 96h
>  Remaining Estimate: 96h
>
> Support loading data in VW format. VW format is used fairly widely and has support for namespaces, importance weighting and multi label and cost sensitive multi class classification formats.
> We can support this just as we support avro and csv formats today .
> It probably belongs to a new package say spark-vw but this JIRA is simply to track and discuss the issue of supporting VW format.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org