[
https://issues.apache.org/jira/browse/SPARK-7372?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sean Owen resolved SPARK-7372.
------------------------------
Resolution: Won't Fix
This should be a question on user@ I think. It would better to build this once
than specialize it several times.
If there were some different, special way to handle mutliclass in SVM that took
advantage of how SVMs worked, then it might make sense to support some
SVM-specific implementation. (For example, you certainly don't need one-vs-all
to do multiclass in decision trees.) But I don't believe there is for SVM.
> Multiclass SVM - One vs All wrapper
> -----------------------------------
>
> Key: SPARK-7372
> URL: https://issues.apache.org/jira/browse/SPARK-7372
> Project: Spark
> Issue Type: Question
> Components: MLlib
> Reporter: Renat Bekbolatov
> Priority: Trivial
>
> I was wondering if we want to have a some support for multiclass SVM in
> MLlib, for example, through a simple wrapper over binary SVM classifiers with
> OVA.
> There is already WIP for ML pipeline generalization: SparkSPARK-7015,
> Multiclass to Binary Reduction
> However, if users prefer to just have basic OVA version that runs against
> SVMWithSGD, they might be able to use it.
> Here is a code sketch:
> https://github.com/Bekbolatov/spark/commit/463d73323d5f08669d5ae85dc9791b036637c966
> Maybe this could live in a 3rd party utility library (outside Spark MLlib).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
