You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@madlib.apache.org by "Frank McQuillan (JIRA)" <ji...@apache.org> on 2018/05/01 23:35:00 UTC

[jira] [Updated] (MADLIB-1178) Improve performance of DT/RF with large feature vectors

     [ https://issues.apache.org/jira/browse/MADLIB-1178?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Frank McQuillan updated MADLIB-1178:
------------------------------------
    Fix Version/s:     (was: v1.15)
                   v2.0

> Improve performance of DT/RF with large feature vectors
> -------------------------------------------------------
>
>                 Key: MADLIB-1178
>                 URL: https://issues.apache.org/jira/browse/MADLIB-1178
>             Project: Apache MADlib
>          Issue Type: Improvement
>          Components: Module: Decision Tree
>            Reporter: Frank McQuillan
>            Priority: Major
>             Fix For: v2.0
>
>
> In the course of doing this story
> https://issues.apache.org/jira/browse/MADLIB-1173
> it was observed that handling large feature vectors could be done more efficiently.
> Story
> As a MADlib developer
> I want to improve the performance of DT/RF with large feature vectors
> So that run-times are faster
> Acceptance
> 1) Run performance tests with feature vectors > 1600 and compare run-times with and without this story's improvements.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)