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 2014/09/30 21:44:34 UTC
[jira] [Commented] (SPARK-2692) Decision Tree API update
[ https://issues.apache.org/jira/browse/SPARK-2692?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14153647#comment-14153647 ]
Joseph K. Bradley commented on SPARK-2692:
------------------------------------------
Closing this since it is part of the new API JIRA: [https://issues.apache.org/jira/browse/SPARK-1856]
> Decision Tree API update
> ------------------------
>
> Key: SPARK-2692
> URL: https://issues.apache.org/jira/browse/SPARK-2692
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Affects Versions: 1.0.0
> Reporter: Joseph K. Bradley
> Assignee: Joseph K. Bradley
>
> Split Decision Tree API into separate Classifier and Regressor classes.
> Details:
> (a) Split classes: E.g.: DecisionTree --> DecisionTreeClassifier and DecisionTreeRegressor
> (b) Included print() function for human-readable model descriptions
> (c) Renamed Strategy to *Params. Changed to take strings instead of special types.
> (d) Made configuration classes (Impurity, QuantileStrategy) private to mllib.
> (e) Changed meaning of maxDepth by 1 to match scikit-learn and rpart.
> (f) Removed static train() functions in favor of using Params classes.
> (g) Introduced DatasetInfo class for metadata.
--
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