[jira] [Comment Edited] (SPARK-13030) Change OneHotEncoder to Estimator

["Nick Pentreath (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-13030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15431319#comment-15431319 ] 

Nick Pentreath edited comment on SPARK-13030 at 8/22/16 6:08 PM:
-----------------------------------------------------------------

Yes I also agree OHE needs to be an {{Estimator}} in order to actually be usable in a pipeline. Alternative is to have a "stateful" transformer - but IMO estimator makes more sense here. 

The issue we face is that OHE in 2.0 is locked down and we can't break things now - since it's no longer {{Experimental}}.

Though in many senses this can be viewed as a bug?!


was (Author: mlnick):
Yes I also agree OHE needs to be an {{Estimator}} in order to actually be usable in a pipeline. Alternative is to have a "stateful" transformer - but IMO estimator makes more sense here. 

The issue we face is that OHE in 2.0 is locked down and we can't break things now - since it's no longer {{Experimental}}.

> Change OneHotEncoder to Estimator
> ---------------------------------
>
>                 Key: SPARK-13030
>                 URL: https://issues.apache.org/jira/browse/SPARK-13030
>             Project: Spark
>          Issue Type: Improvement
>          Components: ML
>    Affects Versions: 1.6.0
>            Reporter: Wojciech Jurczyk
>
> OneHotEncoder should be an Estimator, just like in scikit-learn (http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html).
> In its current form, it is impossible to use when number of categories is different between training dataset and test dataset.



--
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