You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Nick Pentreath (JIRA)" <ji...@apache.org> on 2017/07/14 10:38:00 UTC
[jira] [Comment Edited] (SPARK-21416) Emit Raw Prediction Scores in
DecisionTree Classification Model
[ https://issues.apache.org/jira/browse/SPARK-21416?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16087161#comment-16087161 ]
Nick Pentreath edited comment on SPARK-21416 at 7/14/17 10:37 AM:
------------------------------------------------------------------
This is in Spark 2.2, which also adds probability.
was (Author: mlnick):
This is in Spark 2.2
> Emit Raw Prediction Scores in DecisionTree Classification Model
> ---------------------------------------------------------------
>
> Key: SPARK-21416
> URL: https://issues.apache.org/jira/browse/SPARK-21416
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Affects Versions: 2.0.1
> Reporter: Aman Rawat
>
> DecisionTreeClassificationModel today emits only the final prediction score (index for the class). However, it's often required to know the raw prediction score for each class as well. This is already available in the underlying model, but not exposed in "ML" (i.e. DataFrame based) interace - DecisionTreeClassificationModel.
> The transformer's output can be changed to include both "prediction" and "rawPrediction" columns.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org