[
https://issues.apache.org/jira/browse/SPARK-13676?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xiangrui Meng updated SPARK-13676:
----------------------------------
Target Version/s: 2.0.0
> Fix mismatched default values for regParam in LogisticRegression
> ----------------------------------------------------------------
>
> Key: SPARK-13676
> URL: https://issues.apache.org/jira/browse/SPARK-13676
> Project: Spark
> Issue Type: Bug
> Components: ML, MLlib
> Reporter: Dongjoon Hyun
> Assignee: Dongjoon Hyun
> Fix For: 2.0.0
>
>
> The default value of regularization parameter for `LogisticRegression`
> algorithm is different in Scala and Python. We should provide the same value.
> {code:title=Scala|borderStyle=solid}
> scala> new org.apache.spark.ml.classification.LogisticRegression().getRegParam
> res0: Double = 0.0
> {code}
> {code:title=Python|borderStyle=solid}
> >>> from pyspark.ml.classification import LogisticRegression
> >>> LogisticRegression().getRegParam()
> 0.1
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
