[ https://issues.apache.org/jira/browse/SPARK-30661?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17478678#comment-17478678 ]
Sean R. Owen commented on SPARK-30661: -------------------------------------- How much difference does it make? I'm weighing the cost of a new user parameter and more code vs benefit. I would, I suppose, not expect clustering input to be exceptionally sparse. Sparse often implies high dimensional, and everything is far from everything in high dimensions, so clustering makes less sense. If anything that is an argument for your change. I am just wondering out loud about even whether to change the default to the blocked impl, if this proceeds. > KMeans blockify input vectors > ----------------------------- > > Key: SPARK-30661 > URL: https://issues.apache.org/jira/browse/SPARK-30661 > Project: Spark > Issue Type: Sub-task > Components: ML, PySpark > Affects Versions: 3.0.0 > Reporter: zhengruifeng > Assignee: zhengruifeng > Priority: Minor > -- This message was sent by Atlassian Jira (v8.20.1#820001) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org