You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2015/02/13 20:23:11 UTC

[jira] [Commented] (SPARK-5804) Explicitly manage cache in Crossvalidation k-fold loop

    [ https://issues.apache.org/jira/browse/SPARK-5804?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14320607#comment-14320607 ] 

Apache Spark commented on SPARK-5804:
-------------------------------------

User 'petro-rudenko' has created a pull request for this issue:
https://github.com/apache/spark/pull/4595

> Explicitly manage cache in Crossvalidation k-fold loop
> ------------------------------------------------------
>
>                 Key: SPARK-5804
>                 URL: https://issues.apache.org/jira/browse/SPARK-5804
>             Project: Spark
>          Issue Type: Improvement
>          Components: ML
>    Affects Versions: 1.3.0
>            Reporter: Peter Rudenko
>            Priority: Minor
>
> On a big dataset explicitly unpersist train and validation folds allows to load more data into memory in the next loop iteration. On my environment (single node 8Gb worker RAM, 2 GB dataset file, 3 folds for cross validation), saved more than 5 minutes.



--
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