[ https://issues.apache.org/jira/browse/SPARK-5597?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14305993#comment-14305993 ]
Joseph K. Bradley commented on SPARK-5597: ------------------------------------------ I'm partway done with a PR for this in the Parquet-based format, following the example of my PR for GLMs and NaiveBayes. It's flattening nodes into Rows in a DataFrame, which should hopefully make for efficient columnar storage with Parquet. It would be great to get PMML export for this too though. > Model import/export for DecisionTree and ensembles > -------------------------------------------------- > > Key: SPARK-5597 > URL: https://issues.apache.org/jira/browse/SPARK-5597 > Project: Spark > Issue Type: Sub-task > Components: MLlib > Affects Versions: 1.3.0 > Reporter: Joseph K. Bradley > Assignee: Joseph K. Bradley > > See parent JIRA for more info. -- 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