[SPARK-5317]Set BoostingStrategy.defaultParams With Enumeration Algo.Classification or Algo.Regression#4103
[SPARK-5317]Set BoostingStrategy.defaultParams With Enumeration Algo.Classification or Algo.Regression#4103Peishen-Jia wants to merge 8 commits intoapache:masterfrom Peishen-Jia:stragetyAlgo
Conversation
|
Can one of the admins verify this patch? |
|
ok to test |
|
Test build #25764 has started for PR 4103 at commit
|
|
Test build #25764 has finished for PR 4103 at commit
|
|
Test PASSed. |
docs/mllib-ensembles.md
Outdated
There was a problem hiding this comment.
This doesn't work in Java. You need at least "Algo.Classification()`.
There was a problem hiding this comment.
Seems that I am a little careless about the docs of Java version. I will update it.
|
Test build #25865 has started for PR 4103 at commit
|
|
Test build #25865 has finished for PR 4103 at commit
|
|
Test PASSed. |
|
Test build #25933 has started for PR 4103 at commit
|
|
Test build #25933 has finished for PR 4103 at commit
|
|
Test PASSed. |
There was a problem hiding this comment.
This is my bad. In Scala, the parameter name is part of the API. So let's not rename algo to algoStr.
|
Test build #25943 has started for PR 4103 at commit
|
|
LGTM pending Jenkins. |
|
Test build #25943 has finished for PR 4103 at commit
|
|
Test PASSed. |
JIRA Issue: https://issues.apache.org/jira/browse/SPARK-5317
When setting the BoostingStrategy.defaultParams("Classification"), It's more straightforward to set it with the Enumeration Algo.Classification, just like BoostingStragety.defaultParams(Algo.Classification).
I overload the method BoostingStragety.defaultParams().