Github user psuszyns commented on a diff in the pull request:
https://github.com/apache/spark/pull/12419#discussion_r61326101
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
---
@@ -379,15 +379,21 @@ class RowMatrix @Since("1.0.0") (
*
* Note that this cannot be computed on matrices with more than 65535
columns.
*
- * @param k number of top principal components.
+ * @param filter either the number of top principal components or
variance
+ * retained by the minimal set of principal components.
* @return a matrix of size n-by-k, whose columns are principal
components, and
* a vector of values which indicate how much variance each principal
component
* explains
*/
@Since("1.6.0")
- def computePrincipalComponentsAndExplainedVariance(k: Int): (Matrix,
Vector) = {
+ def computePrincipalComponentsAndExplainedVariance(filter: Either[Int,
Double])
--- End diff --
@sethah @jodersky It looks like the comment Since("1.6.0") is false becaue
this method is not available in spark 1.6 - this change was merged to master
instead of 1.6 branch. Do you still consider this change as API breaking given
that it modifies API that wasn't yet released? If yes then I'll do as @jodersky
said and introduce a new method and move common code to a new private one. I'd
really like to have this feature in MLlib version because I use it.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
