[
https://issues.apache.org/jira/browse/SPARK-9963?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Joseph K. Bradley updated SPARK-9963:
-------------------------------------
Target Version/s: 1.6.0
> ML RandomForest cleanup: Move predictNodeIndex to LearningNode
> --------------------------------------------------------------
>
> Key: SPARK-9963
> URL: https://issues.apache.org/jira/browse/SPARK-9963
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Reporter: Joseph K. Bradley
> Assignee: Luvsandondov Lkhamsuren
> Priority: Trivial
> Labels: starter
>
> (updated form original description)
> Move ml.tree.impl.RandomForest.predictNodeIndex to LearningNode.
> We need to keep it as a separate method from Node.predictImpl because (a) it
> needs to operate on binned features and (b) it needs to return the node ID,
> not the node (because it can return the ID for nodes which do not yet exist).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
