[SPARK-3702] Standardize MLlib classes for learners, models

• Type: Sub-task
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Fix Version/s: 1.5.0
• Component/s: MLlib
• Assignee: Joseph K. Bradley
• Reporter: Joseph K. Bradley
• Created: 26/Sep/14 20:49
• Updated: 24/Sep/15 22:27
• Resolved: 24/Sep/15 22:27

Description

Summary: Create a class hierarchy for learning algorithms and the models those algorithms produce.

This is a super-task of several sub-tasks (but JIRA does not allow subtasks of subtasks). See the "requires" links below for subtasks.

Goals:

• give intuitive structure to API, both for developers and for generated documentation
• support meta-algorithms (e.g., boosting)
• support generic functionality (e.g., evaluation)
• reduce code duplication across classes

Design doc for class hierarchy

Issue Links

• is depended upon by: SPARK-4591 Algorithm/model parity for spark.ml (Scala)
• is related to: SPARK-3507 Create RegressionLearner trait and make some currect code implement it
• is related to: SPARK-3251 Clarify learning interfaces
• relates to: SPARK-10817 ML abstraction umbrella
• requires: SPARK-4789 Standardize ML Prediction APIs
• requires: SPARK-5995 Make ML Prediction Developer APIs public
• links to: [Github] Pull Request #3427 (jkbradley)