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

Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2014/08/01 23:57:39 UTC

[jira] [Commented] (SPARK-2796) DecisionTree bug with ordered categorical features

    [ https://issues.apache.org/jira/browse/SPARK-2796?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14083018#comment-14083018 ] 

Apache Spark commented on SPARK-2796:
-------------------------------------

User 'jkbradley' has created a pull request for this issue:
https://github.com/apache/spark/pull/1720

> DecisionTree bug with ordered categorical features
> --------------------------------------------------
>
>                 Key: SPARK-2796
>                 URL: https://issues.apache.org/jira/browse/SPARK-2796
>             Project: Spark
>          Issue Type: Bug
>          Components: MLlib
>    Affects Versions: 1.0.0
>            Reporter: Joseph K. Bradley
>
> In DecisionTree, the method sequentialBinSearchForOrderedCategoricalFeatureInClassification() indexed bins from 0 to (math.pow(2, featureCategories.toInt - 1) - 1).  This upper bound is the bound for unordered categorical features, not ordered ones.  The upper bound should be the arity (i.e., max value) of the feature.



--
This message was sent by Atlassian JIRA
(v6.2#6252)