You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "Joseph K. Bradley (JIRA)" <ji...@apache.org> on 2016/05/24 19:07:13 UTC

[jira] [Created] (SPARK-15510) SparkR NaiveBayes should not require label to have NominalAttribute

Joseph K. Bradley created SPARK-15510:
-----------------------------------------

             Summary: SparkR NaiveBayes should not require label to have NominalAttribute
                 Key: SPARK-15510
                 URL: https://issues.apache.org/jira/browse/SPARK-15510
             Project: Spark
          Issue Type: Improvement
          Components: ML, SparkR
            Reporter: Joseph K. Bradley


Currently, SparkR's NaiveBayes API fails if the label is numeric.  It works if the label is a String.  This is because NaiveBayesWrapper requires that the input column be annotated with NominalAttribute, which is created when Strings are indexed by RFormula.  We should eliminate this restriction since it causes failures easily, such as when trying to run NB on LibSVM datasets.



--
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