[
https://issues.apache.org/jira/browse/FLINK-31030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17733336#comment-17733336
]
xingyuan cheng commented on FLINK-31030:
----------------------------------------
I am interested in this, and I will start working on it after I sort out the
execution process of the BinaryClassificationEvaluator#transform method
> Support more binary classification evaluation metrics.
> ------------------------------------------------------
>
> Key: FLINK-31030
> URL: https://issues.apache.org/jira/browse/FLINK-31030
> Project: Flink
> Issue Type: Improvement
> Components: Library / Machine Learning
> Reporter: Fan Hong
> Priority: Major
>
> Current `BinaryClassificationEvaluator` only supports 'areaUnderROC',
> 'areaUnderPR', 'ks' and 'areaUnderLorenz'. We should support more evaluation
> metrics, some of which are basic ones, e.g., precision, recall, F-measure,
> and so on.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
