[SPARK-16843] Select features according to a percentile of the highest scores of ChiSqSelector

• Type: New Feature
• Status: Resolved
• Priority: Minor
• Resolution: Duplicate
• Component/s: MLlib
• Flags: Patch
• Assignee: Unassigned
• Reporter: Peng Meng
• Created: 02/Aug/16 01:36
• Updated: 14/Aug/16 11:15
• Resolved: 14/Aug/16 11:15

Description

It would be handy to add a percentile Param to ChiSqSelector, as in the scikit-learn one: http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectPercentile.html

Issue Links

• duplicates: SPARK-17017 Add a chiSquare Selector based on False Positive Rate (FPR) test
• links to: [Github] Pull Request #14449 (mpjlu)