[ https://issues.apache.org/jira/browse/FLINK-2297?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14609791#comment-14609791 ]
ASF GitHub Bot commented on FLINK-2297: --------------------------------------- Github user thvasilo commented on a diff in the pull request: https://github.com/apache/flink/pull/874#discussion_r33660746 --- Diff: flink-staging/flink-ml/src/main/scala/org/apache/flink/ml/pipeline/Predictor.scala --- @@ -121,7 +121,7 @@ object Predictor { input.mapWithBcVariable(model){ (element, model) => { - (element, predictOperation.predict(element, model)) + (element, predictOperation.predict(element, model, resultingParameters)) --- End diff -- I could have a `predictParameters` variable in the SVM `PredictOperation` and assign it a value in `getModel` then. Does that sound better? > Add threshold setting for SVM binary predictions > ------------------------------------------------ > > Key: FLINK-2297 > URL: https://issues.apache.org/jira/browse/FLINK-2297 > Project: Flink > Issue Type: Improvement > Components: Machine Learning Library > Reporter: Theodore Vasiloudis > Assignee: Theodore Vasiloudis > Priority: Minor > Labels: ML > Fix For: 0.10 > > > Currently SVM outputs the raw decision function values when using the predict > function. > We should have instead the ability to set a threshold above which examples > are labeled as positive (1.0) and below negative (-1.0). Then the prediction > function can be directly used for evaluation. -- This message was sent by Atlassian JIRA (v6.3.4#6332)