[jira] [Commented] (SPARK-12230) WeightedLeastSquares.fit() should handle division by zero properly if standard deviation of target variable is zero.

2015-12-14 Thread Apache Spark (JIRA)

[ 
https://issues.apache.org/jira/browse/SPARK-12230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15056360#comment-15056360
 ] 

Apache Spark commented on SPARK-12230:
--

User 'iyounus' has created a pull request for this issue:
https://github.com/apache/spark/pull/10274

> WeightedLeastSquares.fit() should handle division by zero properly if 
> standard deviation of target variable is zero.
> 
>
> Key: SPARK-12230
> URL: https://issues.apache.org/jira/browse/SPARK-12230
> Project: Spark
>  Issue Type: Bug
>  Components: ML
>Reporter: Imran Younus
>Priority: Trivial
>
> This is a TODO in WeightedLeastSquares.fit() method. If the standard 
> deviation of the target variablel is zero, then the regression is 
> meaningless. I think the fit() method should inform the user and exit nicely.



--
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



[jira] [Commented] (SPARK-12230) WeightedLeastSquares.fit() should handle division by zero properly if standard deviation of target variable is zero.

2015-12-08 Thread Imran Younus (JIRA)

[ 
https://issues.apache.org/jira/browse/SPARK-12230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15047985#comment-15047985
 ] 

Imran Younus commented on SPARK-12230:
--

I can work on this.

> WeightedLeastSquares.fit() should handle division by zero properly if 
> standard deviation of target variable is zero.
> 
>
> Key: SPARK-12230
> URL: https://issues.apache.org/jira/browse/SPARK-12230
> Project: Spark
>  Issue Type: Bug
>  Components: ML
>Reporter: Imran Younus
>Priority: Trivial
>
> This is a TODO in WeightedLeastSquares.fit() method. If the standard 
> deviation of the target variablel is zero, then the regression is 
> meaningless. I think the fit() method should inform the user and exit nicely.



--
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