Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/3343#discussion_r20499467
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala ---
@@ -797,6 +797,7 @@ object ALS {
* @param rank number of features to use
* @param iterations number of iterations of ALS (recommended: 10-20)
* @param lambda regularization factor (recommended: 0.01)
+ * @param alpha confidence parameter (only applies when
immplicitPrefs = true)
--- End diff --
So, while we're here, maybe clean a few more things up. "immplicit" is
misspelled, and since this is documentation for `trainImplicit`, there is no
`implicitPrefs` parameter anyway. It's, erm, _implicitly_ true. But these were
just true in the text you copied, so can perhaps be fixed elsewhere.
It's really 1 + alpha*R that is the confidence value. alpha sort of
controls how difference confidence is in an observed and unobserved
interaction. Maybe it's nice to bother to explain a tiny bit more about what
this is, in the class scaladoc, and refer to it. While we're here.
---
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]
