[
https://issues.apache.org/jira/browse/SPARK-6529?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14501457#comment-14501457
]
Joseph K. Bradley commented on SPARK-6529:
------------------------------------------
I agree it can transform a {code}word: String{code} into multiple output types.
For that, let's follow the example in the Classifiers, which have multiple
output columns. That will be simpler and allow users to turn output columns on
and off. See the Classifier output columns "prediction" and "rawPrediction"
A tougher problem is handling a transform which takes a Vector (as in the
spark.mllib package). I think that we should not support Vectors as inputs for
now, but we can add that later by making transform() smart and recognize the
input column type.
> Word2Vec transformer
> --------------------
>
> Key: SPARK-6529
> URL: https://issues.apache.org/jira/browse/SPARK-6529
> Project: Spark
> Issue Type: Sub-task
> Components: ML
> Reporter: Xusen Yin
> Assignee: Xusen Yin
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
