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

Posted to issues@hivemall.apache.org by "Makoto Yui (JIRA)" <ji...@apache.org> on 2019/03/11 09:00:09 UTC

[jira] [Created] (HIVEMALL-243) Fixed nominal variable handling in DecisionTree and RegressionTree

Makoto Yui created HIVEMALL-243:
-----------------------------------

             Summary: Fixed nominal variable handling in DecisionTree and RegressionTree
                 Key: HIVEMALL-243
                 URL: https://issues.apache.org/jira/browse/HIVEMALL-243
             Project: Hivemall
          Issue Type: Task
    Affects Versions: 0.5.2
            Reporter: Makoto Yui
            Assignee: Makoto Yui
             Fix For: 0.6.0


For NOMINAL variable, the maximum attribute index 'm' is used for computing splits.

This cause performance issues for sparse nominal variables. So, revise this handling for a better performance.

https://github.com/apache/incubator-hivemall/blob/master/core/src/main/java/hivemall/smile/classification/DecisionTree.java#L703



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)