[jira] [Updated] (SPARK-6025) Helper method for GradientBoostedTrees to compute validation error

["Joseph K. Bradley (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/SPARK-6025?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Joseph K. Bradley updated SPARK-6025:
-------------------------------------
    Assignee: Manoj Kumar

> Helper method for GradientBoostedTrees to compute validation error
> ------------------------------------------------------------------
>
>                 Key: SPARK-6025
>                 URL: https://issues.apache.org/jira/browse/SPARK-6025
>             Project: Spark
>          Issue Type: New Feature
>          Components: MLlib
>    Affects Versions: 1.3.0
>            Reporter: Joseph K. Bradley
>            Assignee: Manoj Kumar
>            Priority: Minor
>             Fix For: 1.4.0
>
>
> Create a helper method for computing the error at each iteration of boosting.  This should be used post-hoc to compute the error efficiently on a new dataset.
> E.g.:
> {code}
> def evaluateEachIteration(data: RDD[LabeledPoint], evaluator): Array[Double]
> {code}
> Notes:
> * It should run in the same big-O time as predict() by keeping a running total (residual).
> * A different method name could be good.
> * It could take an evaluator and/or could evaluate using the training metric by default.



--
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