[SPARK-14681] Provide label/impurity stats for spark.ml decision tree nodes

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Won't Do
• Component/s: ML
• Assignee: Weichen Xu
• Reporter: Joseph K. Bradley
• Created: 16/Apr/16 08:01
• Updated: 07/Oct/18 17:08
• Resolved: 02/Oct/18 21:24

Description

Currently, spark.ml decision trees provide all node info except for the aggregated stats about labels and impurities. This task is to provide those publicly. We need to choose a good API for it, so we should discuss the design on this issue before implementing it.

Issue Links

• is duplicated by: SPARK-23824 Make inpurityStats publicly accessible in ml.tree.Node
• is required by: SPARK-14376 spark.ml parity for trees
• links to: [Github] Pull Request #17466 (shaynativ)
• links to: [Github] Pull Request #20758 (WeichenXu123)
• links to: [Github] Pull Request #20786 (WeichenXu123)
• links to: [Github] Pull Request #22492 (WeichenXu123)
• links to: [Github] Pull Request #22492 (WeichenXu123)
• links to: [Github] Pull Request #22618 (mengxr)