[
https://issues.apache.org/jira/browse/SPARK-3195?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sean Owen updated SPARK-3195:
-
Priority: Minor (was: Major)
Target Version/s: (was: 1.3.0)
Fix Version/s: (was: 1.3.0)
Labels: (was: test)
This sounds like a question more than a JIRA, and questions are better
discussed on the mailing list. Can you clarify what you want, and propose a PR,
or else close?
Can you add some statistics to do logistic regression better in mllib?
--
Key: SPARK-3195
URL: https://issues.apache.org/jira/browse/SPARK-3195
Project: Spark
Issue Type: New Feature
Components: MLlib
Reporter: miumiu
Priority: Minor
Original Estimate: 1m
Remaining Estimate: 1m
HI，
In logistic regression model practice，Test of regression coefficient and
whole model fitting are very important.Can you add some effective support on
these Aspects?
Such as,The likelihood ratio test or the wald test is offer used for test
of coefficient,and the Hosmer-Lemeshow test is used for evaluate the model
fitting.
Learning that we have ROC and Precision-Recall already,but can you also
provide KS statistic,which is mostly used in Model evaluation aspect?
--
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
