[
https://issues.apache.org/jira/browse/SPARK-12531?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15073159#comment-15073159
]
Joseph K. Bradley commented on SPARK-12531:
-------------------------------------------
[~gauravkumar37] The current plan for these stats is to provide them under
DataFrames since they are useful beyond ML: [SPARK-6761] should handle
(approximate) median. I don't think there's a JIRA for mode yet, but it'd be
related at least to the count-min-sketch JIRA linked from the parent of
[SPARK-6761]. I'd recommend voting/commenting on those JIRAs for these stats.
I'll close this JIRA since this will be done outside of MLlib.
> Add median and mode to Summary statistics
> -----------------------------------------
>
> Key: SPARK-12531
> URL: https://issues.apache.org/jira/browse/SPARK-12531
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Affects Versions: 1.5.2
> Reporter: Gaurav Kumar
> Priority: Minor
>
> Summary statistics should also include calculating median and mode in
> addition to mean, variance and others.
--
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
