[
https://issues.apache.org/jira/browse/SPARK-9690?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14660403#comment-14660403
]
Joseph K. Bradley commented on SPARK-9690:
------------------------------------------
I agree this is a useful feature, but this is actually indicating a bug in SQL,
where it think seed = 0 means no seed. I'll report that.
> Adding the possibility to set the seed of the rand in the CrossValidator fold
> -----------------------------------------------------------------------------
>
> Key: SPARK-9690
> URL: https://issues.apache.org/jira/browse/SPARK-9690
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Affects Versions: 1.4.1
> Reporter: Martin Menestret
> Priority: Minor
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The fold in the ML CrossValidator depends on a rand whose seed is set to 0
> and it leads the sql.functions rand to call sc._jvm.functions.rand() with no
> seed.
> In order to be able to unit test a Cross Validation it would be a good idea
> to be able to set this seed so the output of the cross validation (with a
> featureSubsetStrategy set to "all") would always be the same.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
