[
https://issues.apache.org/jira/browse/SPARK-1675?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14039944#comment-14039944
]
Sean Owen commented on SPARK-1675:
----------------------------------
Is this still valid? Looking at the code, PCA is computed as the SVD of the
covariance matrix. The means implicitly don't matter. they are not explicitly
subtracted, and do not matter. Or is there still a doc change desired?
> Make clear whether computePrincipalComponents centers data
> ----------------------------------------------------------
>
> Key: SPARK-1675
> URL: https://issues.apache.org/jira/browse/SPARK-1675
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Affects Versions: 1.0.0
> Reporter: Sandy Ryza
> Assignee: Sandy Ryza
>
--
This message was sent by Atlassian JIRA
(v6.2#6252)
