Github user chouqin commented on a diff in the pull request:
https://github.com/apache/spark/pull/2332#discussion_r17355688
--- Diff:
mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala ---
@@ -674,6 +676,45 @@ class DecisionTreeSuite extends FunSuite with
LocalSparkContext {
validateClassifier(model, arr, 0.6)
}
+ test("split must satisfy min instances per node requirements") {
--- End diff --
minInstancesPerNode's default value is 1, which is tested by other test
cases.
If I change `strategy.minInstancesPerNode` to 2(which is 4 right now),
other parts don't need to change, because no there are only three instances, no
split can make left and rightchild to have 2 instances. So I think setting
`minInstancesPerNode` to 2 is more reasonable than 4 in this test case. Does
this change satisfy your needs? Or should I increase the instances number and
test `minInstancesPerNode` is 2 and 4 at the same time?
---
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]
