Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/16149#discussion_r91901487
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/regression/GeneralizedLinearRegressionSuite.scala
---
@@ -715,7 +715,7 @@ class GeneralizedLinearRegressionSuite
val datasetWithWeight = Seq(
Instance(1.0, 1.0, Vectors.dense(0.0, 5.0).toSparse),
Instance(0.5, 2.0, Vectors.dense(1.0, 2.0)),
- Instance(1.0, 3.0, Vectors.dense(2.0, 1.0)),
+ Instance(1.0, 0.3, Vectors.dense(2.0, 1.0)),
--- End diff --
I still think that the case where the weight rounds to zero (e.g. 0.3) and
the case where the weight rounds to something non-zero are different cases and
both should be tested. The first case we are just testing that we disregard
that sample entirely, the second case we are testing that we round to an
integer and then proceed with the normal calculation. One thing I can think of
is that if R were doing its rounding differently (e.g. always rounding down)
and we were rounding to the nearest integer, then there would be an
inconsistency and we wouldn't know 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]
