[SPARK-5031] ml.LogisticRegression score column should be renamed probability

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 1.2.0
• Fix Version/s: 1.3.0
• Component/s: ML
• Target Version/s: 1.3.0
• Assignee: Joseph K. Bradley
• Reporter: Joseph K. Bradley
• Created: 31/Dec/14 06:56
• Updated: 06/Feb/15 07:45
• Resolved: 06/Feb/15 07:45

Description

In the spark.ml package, LogisticRegression has an output column "score" which contains the estimated probability of label 1. "Score" is a very overloaded term, so "probability" would be better.

Issue Links

• links to: [Github] Pull Request #3637 (jkbradley)