[SPARK-19319] SparkR Kmeans summary returns error when the cluster size doesn't equal to k

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 2.1.1, 2.2.0
• Component/s: ML, SparkR
• Target Version/s: 2.1.1, 2.2.0
• Assignee: Miao Wang
• Reporter: Miao Wang
• Created: 21/Jan/17 01:04
• Updated: 12/Feb/17 18:50
• Resolved: 01/Feb/17 05:17

Description

When Kmeans using initMode = "random" and some random seed, it is possible the actual cluster size doesn't equal to the configured `k`.

In this case, summary(model) returns error due to the number of cols of coefficient matrix doesn't equal to k.

Issue Links

• is related to: SPARK-3261 KMeans clusterer can return duplicate cluster centers
• links to: [Github] Pull Request #16666 (wangmiao1981)
• links to: [Github] Pull Request #16761 (wangmiao1981)