[
https://issues.apache.org/jira/browse/SPARK-13545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
DB Tsai resolved SPARK-13545.
-----------------------------
Resolution: Fixed
Fix Version/s: 2.0.0
Issue resolved by pull request 11424
[https://github.com/apache/spark/pull/11424]
> Make MLlib LogisticRegressionWithLBFGS's default parameters consistent in
> Scala and Python
> ------------------------------------------------------------------------------------------
>
> Key: SPARK-13545
> URL: https://issues.apache.org/jira/browse/SPARK-13545
> Project: Spark
> Issue Type: Improvement
> Components: MLlib, PySpark
> Reporter: Yanbo Liang
> Priority: Minor
> Fix For: 2.0.0
>
>
> * The default value of regParam of PySpark MLlib LogisticRegressionWithLBFGS
> should be consistent with Scala which is 0.0. (This is also consistent with
> ML LogisticRegression.)
> * BTW, if we use a known updater(L1 or L2) for binary classification,
> LogisticRegressionWithLBFGS will call the ML implementation. We should update
> the API doc to clarifying numCorrections will have no effect if we fall into
> that route.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
