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 2019/04/29 19:27:00 UTC

[jira] [Updated] (MADLIB-976) Random Forest - extremely long training time

     [ https://issues.apache.org/jira/browse/MADLIB-976?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Frank McQuillan updated MADLIB-976:
-----------------------------------
    Fix Version/s: v2.0

> Random Forest - extremely long training time
> --------------------------------------------
>
>                 Key: MADLIB-976
>                 URL: https://issues.apache.org/jira/browse/MADLIB-976
>             Project: Apache MADlib
>          Issue Type: Bug
>          Components: Module: Random Forest
>            Reporter: Rashmi Raghu
>            Priority: Major
>             Fix For: v2.0
>
>
> When running Random Forest training function on a modest data set it took a long time - much longer than expected or desired. The training data set has around 8000 rows and 400 features. Several models on similar data all took around 40,000 seconds to run.  Each time we used 100 trees and 14 random features selected. Dataset shared offline.



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