[SPARK-10592] deprecate weights and use coefficients instead in ML models

• Type: Improvement
• Status: Resolved
• Priority: Critical
• Resolution: Fixed
• Fix Version/s: 1.6.0
• Component/s: ML, PySpark
• Target Version/s: 1.6.0
• Assignee: Kai Jiang
• Reporter: Xiangrui Meng
• Shepherd: Xiangrui Meng
• Created: 14/Sep/15 18:42
• Updated: 25/May/16 01:23
• Resolved: 03/Nov/15 00:12

Description

The name `weights` becomes confusing as we are supporting weighted instanced. As discussed in https://github.com/apache/spark/pull/7884, we want to deprecate `weights` and use `coefficients` instead:

• Deprecate but do not remove `weights`.
• Only make changes under `spark.ml`.

Issue Links

• is related to: SPARK-9610 Class and instance weighting for ML
• links to: [Github] Pull Request #9311 (vectorijk)