[
https://issues.apache.org/jira/browse/SPARK-11861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15018309#comment-15018309
]
Seth Hendrickson commented on SPARK-11861:
------------------------------------------
It's not really different, except that when feature importance for random
forests got implemented it wasn't added to the decision tree API. This would
simply add an API entry point in {{DecisionTreeRegressionModel}} and
{{DecisionTreeClassificationModel}}. Perhaps I'm missing your meaning?
Having a feature importance for Decision Trees will be useful when implementing
a feature importance for Gradient Boosted Trees according to
[SPARK-11730|https://issues.apache.org/jira/browse/SPARK-11730], since GBT
feature importance would likely be some aggregation of feature importance for
individual trees in the ensemble.
> Feature importances for decision trees
> --------------------------------------
>
> Key: SPARK-11861
> URL: https://issues.apache.org/jira/browse/SPARK-11861
> Project: Spark
> Issue Type: New Feature
> Components: ML
> Reporter: Seth Hendrickson
> Priority: Minor
>
> Feature importances should be added to decision trees leveraging the feature
> importance implementation for Random Forests.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
