[
https://issues.apache.org/jira/browse/SPARK-14900?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15271023#comment-15271023
]
Miao Wang commented on SPARK-14900:
-----------------------------------
Yes, "accuracy" makes more sense for binary classification problems. I will
create a JIRA for it and work on it.
For the MulticalssMetrics, I will make changes to deprecate "precision" by
accuracy.
> spark.ml classification metrics should include accuracy
> -------------------------------------------------------
>
> Key: SPARK-14900
> URL: https://issues.apache.org/jira/browse/SPARK-14900
> Project: Spark
> Issue Type: New Feature
> Components: ML
> Reporter: Joseph K. Bradley
> Priority: Minor
>
> To compute "accuracy" (0/1 classification accuracy), users can use
> {{precision}} in MulticlassMetrics and
> MulticlassClassificationEvaluator.metricName. We should also support
> "accuracy" directly as an alias to help users familiar with that name.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
