Details
-
Sub-task
-
Status: Resolved
-
Major
-
Resolution: Duplicate
-
1.5.2
-
None
-
None
Description
"featureImportances" is only exposed at ML not MLlib.
It cannot be used with org.apache.spark.mllib.tree.RandomForest.
To use it requires using RandomForestClassifier of ML to train and create a RandomForestClassificationModel.
Attachments
Issue Links
- duplicates
-
SPARK-11861 Expose feature importances API for decision trees
- Resolved