[
https://issues.apache.org/jira/browse/SPARK-8442?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon resolved SPARK-8442.
---------------------------------
Resolution: Incomplete
> FitTransform method for pipeline
> --------------------------------
>
> Key: SPARK-8442
> URL: https://issues.apache.org/jira/browse/SPARK-8442
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Affects Versions: 1.4.0
> Reporter: Peter Rudenko
> Priority: Major
> Labels: bulk-closed
>
> Currently in pipeline fit's method the data is transformed and keep tracked
> through the whole pipeline. But it returns only PipelineModel, so after need
> to call PipelineModel.transform - and to do the same job twice.
> Need to implement method:
> {code}
> def fitTransform(dataset: Dataframe): (PipelineModel, Dataframe)
> {code}
> That would returned PipelineModel and transformed dataframe.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
