[jira] [Commented] (SPARK-17987) ML Evaluator fails to handle null values in the dataset

["Sean Owen (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-17987?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15584956#comment-15584956 ] 

Sean Owen commented on SPARK-17987:
-----------------------------------

I think this is on purpose. There's no meaningful way to handle a missing value in evaluation like this, so any solution would amount to imputing a value, and the caller can/should do that. That is, what's the contribution to the error metric in this case? 0? infinity? NaN? all of those are problematic.

> ML Evaluator fails to handle null values in the dataset
> -------------------------------------------------------
>
>                 Key: SPARK-17987
>                 URL: https://issues.apache.org/jira/browse/SPARK-17987
>             Project: Spark
>          Issue Type: Improvement
>          Components: ML
>    Affects Versions: 1.6.2, 2.0.1
>            Reporter: bo song
>
> Take the RegressionEvaluator as an example, when the predictionCol is null in a row, en exception "scala.MatchEror" will be thrown. The missing null prediction is a common case, for example when an predictor is missing, or its value is out of bound, almost machine learning models could not produce correct predictions, then null predictions would be returned. Evaluators should handle the null values instead of an exception thrown, the common way to handle missing null values is to ignore them. Besides of the null value, the NAN value need to be handled correctly too. 
> Those three evaluators RegressionEvaluator, BinaryClassificationEvaluator and MulticlassClassificationEvaluator have the same problem.



--
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