The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Bug message when running Keras: Extraction of nominal example value for non-nominal attribute 'RUL'
Hello, I have the following bug below when I tried to run Keras (Deep Neural Net 3 Dense layer with 1 Dropout layer). I've also attached the screenshot of my process. Note that I tried the same process with the different datasets but got no issue. Both datasets predict the numerical value (the label is number, not category). If anyone knows it's a bug or I did something wrong ... please ... please help.
Thank you!
====================================================================================
Thank you!
====================================================================================
Exception: com.rapidminer.example.AttributeTypeException
Message: Extraction of nominal example value for non-nominal attribute 'RUL' is not possible.
Stack trace:
com.rapidminer.example.Example.getNominalValue(Example.java:98)
com.rapidminer.operator.performance.SimpleCriterion.countExample(SimpleCriterion.java:93)
com.rapidminer.operator.performance.AbstractPerformanceEvaluator.evaluate(AbstractPerformanceEvaluator.java:470)
com.rapidminer.operator.performance.AbstractPerformanceEvaluator.evaluate(AbstractPerformanceEvaluator.java:393)
com.rapidminer.operator.performance.AbstractPerformanceEvaluator.doWork(AbstractPerformanceEvaluator.java:256)
com.rapidminer.operator.Operator.execute(Operator.java:1032)
com.rapidminer.operator.execution.SimpleUnitExecutor.execute(SimpleUnitExecutor.java:77)
com.rapidminer.operator.ExecutionUnit$2.run(ExecutionUnit.java:812)
com.rapidminer.operator.ExecutionUnit$2.run(ExecutionUnit.java:807)
java.security.AccessController.doPrivileged(Native Method)
com.rapidminer.operator.ExecutionUnit.execute(ExecutionUnit.java:807)
com.rapidminer.operator.OperatorChain.doWork(OperatorChain.java:423)
com.rapidminer.operator.Operator.execute(Operator.java:1032)
com.rapidminer.Process.executeRoot(Process.java:1378)
com.rapidminer.Process.lambda$executeRootInPool$5(Process.java:1357)
com.rapidminer.studio.concurrency.internal.AbstractConcurrencyContext$AdaptedCallable.exec(AbstractConcurrencyContext.java:328)
java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157)
1
Answers
Sure, no problem. I can share the actual XML with you below.
I suspected that for some reason, the Keras layer transformed my label (or prediction attribute) into nominal data. This is the regression problem and my label is numerical data. There is certainly no problem with data cleaning because I use this same dataset to do one layer ANN (Artificial Neural Net) in RapidMiner before I tried Keras. The problem occurred when applying the model from Keras into the test dataset.
I've also attached the layer in the Keras process for you as well. The problem might come from the last layer. As I understand the last layer should act as an output layer and should be a dense layer with no activation function, right? Please help to correct me if I'm wrong.
=========================================================================