Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/16131#discussion_r91000876
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
---
@@ -505,7 +505,8 @@ object GeneralizedLinearRegression extends
DefaultParamsReadable[GeneralizedLine
override def initialize(y: Double, weight: Double): Double = {
require(y >= 0.0, "The response variable of Poisson family " +
s"should be non-negative, but got $y")
- y
+ // force Poisson mean > 0 to avoid numerical instability in IRLS
--- End diff --
It wouldn't hurt to give a reference to the R source code here if you can,
even just pointing out that this is (sort of) how R deals with it, as
justification. It is a surprisingly big epsilon after all.
---
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]
