[jira] [Comment Edited] (SPARK-16618) Binary classification using Naive bayes

["mahendra singh (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-16618?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15384180#comment-15384180 ] 

mahendra singh edited comment on SPARK-16618 at 7/19/16 2:06 PM:
-----------------------------------------------------------------

in MulticlassMetrics  no option to generate ROC and PR curves points. if i am giving n=2 then it should be binary class classification not multi class  classification .  This is not solution .


was (Author: mahendrasingh):
in MulticlassMetrics  no option to generate ROC and PR curves points. if i am giving n=2 then it should be binary class classification not multi class  classification .  This not solution .

> Binary classification using Naive bayes 
> ----------------------------------------
>
>                 Key: SPARK-16618
>                 URL: https://issues.apache.org/jira/browse/SPARK-16618
>             Project: Spark
>          Issue Type: Bug
>          Components: ML, MLlib
>    Affects Versions: 1.6.2
>            Reporter: mahendra singh
>   Original Estimate: 96h
>  Remaining Estimate: 96h
>
> spark naive bayes does not support for binary classification . I checked with both ML and MLLIB . According to current scenario Naive bayes only support multi class classification . We have to write code for binary classification also .As we know logistic regression support binary classification .   Mean we can not get ROC and PR curve using spark naive , even if we give only two class( category or distinct label values)



--
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