[
https://issues.apache.org/jira/browse/SPARK-31681?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sean R. Owen updated SPARK-31681:
---------------------------------
Docs Text: In Spark 3.0, a multiclass logistic regression in Pyspark will
now (correctly) return LogisticRegressionSummary, not the subclass
BinaryLogisticRegressionSummary. The BinaryLogisticRegressionSummary would not
work in this case anyway.
Description:
{code:java}
def evaluate(self, dataset):
......
java_blr_summary = self._call_java("evaluate", dataset)
return BinaryLogisticRegressionSummary(java_blr_summary)
{code}
We should return LogisticRegressionSummary instead of
BinaryLogisticRegressionSummary for multiclass LogisticRegression
was:
{code:java}
def evaluate(self, dataset):
......
java_blr_summary = self._call_java("evaluate", dataset)
return BinaryLogisticRegressionSummary(java_blr_summary)
{code}
We should return LogisticRegressionSummary instead of
BinaryLogisticRegressionSummary for multiclass LogisticRegression
> Python multiclass logistic regression evaluate should return
> LogisticRegressionSummary
> --------------------------------------------------------------------------------------
>
> Key: SPARK-31681
> URL: https://issues.apache.org/jira/browse/SPARK-31681
> Project: Spark
> Issue Type: Bug
> Components: ML, PySpark
> Affects Versions: 3.1.0
> Reporter: Huaxin Gao
> Priority: Minor
> Labels: release-notes
>
> {code:java}
> def evaluate(self, dataset):
> ......
> java_blr_summary = self._call_java("evaluate", dataset)
> return BinaryLogisticRegressionSummary(java_blr_summary)
> {code}
> We should return LogisticRegressionSummary instead of
> BinaryLogisticRegressionSummary for multiclass LogisticRegression
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
