[SPARK-19282] RandomForestRegressionModel should expose getMaxDepth in R

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 2.1.0
• Fix Version/s: 2.2.0
• Component/s: ML, SparkR
• Target Version/s: 2.2.0
• Assignee: Xin Ren
• Reporter: Nick Lothian
• Created: 19/Jan/17 06:00
• Updated: 27/Apr/17 20:31
• Resolved: 27/Apr/17 20:31

Description

Currently it isn't clear hot to get the max depth of a RandomForestRegressionModel (eg, after doing a grid search)

It is possible to call

regressor._java_obj.getMaxDepth()

but most other decision trees allow

regressor.getMaxDepth()

UPDATE: This is just for Spark R. See SPARK-20498 for Python.

Issue Links

• is blocked by: SPARK-10931 PySpark ML Models should contain Param values
• is cloned by: SPARK-20498 RandomForestRegressionModel should expose getMaxDepth in PySpark
• is related to: SPARK-10931 PySpark ML Models should contain Param values
• links to: [Github] Pull Request #17207 (keypointt)