[
https://issues.apache.org/jira/browse/SPARK-10179?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Shiqiao Du updated SPARK-10179:
-------------------------------
Description:
LogisticRegressionWithSGD does not support Multi-Class input while
LogisticRegressionWithLBFGS is OK.
I found this line in error
```
15/08/24 14:46:57 ERROR DataValidators: Classification labels should be 0 or 1.
Found 50 invalid labels
```
In LogisticRegressionWithLBFGS there is setNumClasses method but
LogisticRegressionWithSGD does not have this method.
was:
LogisticRegressionWithSGD does not support Multi-Class input while
LogisticRegressionWithLBFGS is OK.
I found this line in error
```
15/08/24 14:46:57 ERROR DataValidators: Classification labels should be 0 or 1.
Found 50 invalid labels
```
> LogisticRegressionWithSGD does not multiclass
> ----------------------------------------------
>
> Key: SPARK-10179
> URL: https://issues.apache.org/jira/browse/SPARK-10179
> Project: Spark
> Issue Type: Bug
> Components: MLlib
> Environment: Ubuntu 14.04, spark 1.4.1
> Reporter: Shiqiao Du
>
> LogisticRegressionWithSGD does not support Multi-Class input while
> LogisticRegressionWithLBFGS is OK.
> I found this line in error
> ```
> 15/08/24 14:46:57 ERROR DataValidators: Classification labels should be 0 or
> 1. Found 50 invalid labels
> ```
> In LogisticRegressionWithLBFGS there is setNumClasses method but
> LogisticRegressionWithSGD does not have this method.
--
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
