[SPARK-10022] Scala-Python method/parameter inconsistency check for ML during 1.5 QA

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 1.6.0
• Component/s: ML, MLlib, PySpark
• Assignee: Yanbo Liang
• Reporter: Yanbo Liang
• Created: 16/Aug/15 06:14
• Updated: 24/Nov/15 18:48
• Resolved: 24/Nov/15 18:48

Description

The missing classes for PySpark were listed at SPARK-9663.
Here we check and list the missing method/parameter for ML of PySpark.

Issue Links

• is related to: SPARK-10535 Support for recommendUsersForProducts and recommendProductsForUsers in matrix factorization model for PySpark

Sub-Tasks

• Unified DecisionTreeParams "checkpointInterval" between Scala and Python API.: Resolved
• Python API RF and GBT related params clear up: Resolved
• Implement some common Params for regression in PySpark: Resolved
• Add Python API missing methods for ml.feature: Resolved
• Make StreamingLogisticRegressionWithSGD Python API equals with Scala one: Resolved