[
https://issues.apache.org/jira/browse/SPARK-10387?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14990809#comment-14990809
]
holdenk commented on SPARK-10387:
---------------------------------
Progress - although I'm a little uncertain of what the best API is for this.
I'm thinking that we need to chose one of these:
1) Pick a threshold number of trees above which we skip codegen
2) Make #1 configurable through spark context
3) Provide an explicit codeGen or toCodeGen on the model which the user can
call.
4) Something else entirely
What are peoples thoughts? I'm probably going to proceed with #1 for now and
just try and get something working end to end as a starting point but I'd
appreciate peoples thoughts on how best to expose this functionality.
> Code generation for decision tree
> ---------------------------------
>
> Key: SPARK-10387
> URL: https://issues.apache.org/jira/browse/SPARK-10387
> Project: Spark
> Issue Type: New Feature
> Components: ML
> Reporter: Xiangrui Meng
> Assignee: DB Tsai
>
> Provide code generation for decision tree and tree ensembles. Let's first
> discuss the design and then create new JIRAs for tasks.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
