Null Pointer Exception in Set Role when handling with AdaBoost

Question

1. I have naive bayes implementation on the dataset with  16 attributes, with label which is of type nominal (String)
2. With Naive Bayes I could get the desiered results, when I try to implement adaboost and having Naive Bayes as the Learning Process and providing Input values from the CSV file to the apply model I'm getting a SEVERE: java.lang.NullPointerException in the Set Role Operator. Can you please advice.
3. My goal is apply the CSV sample data on to the trained model outcome from Adaboost algorithm.

seesiva · Answer

Update: When I'm not applying model its generating the model in the result without any issues. In the below xml we can see that output is connected to Result1 and we are also getting the result of the model through the iteration. So when we are applying the model it is causing the issue. Also as per the additional input the log file rm.log gives the following message: SEVERE: Process failed: operator cannot be executed. Check the log messages... java.lang.NullPointerException at com.rapidminer.operator.learner.meta.AdaBoostModel.evaluateSpecialAttributes(AdaBoostModel.java:215) at com.rapidminer.operator.learner.meta.AdaBoostModel.performPrediction(AdaBoostModel.java:168) at com.rapidminer.operator.learner.PredictionModel.apply(PredictionModel.java:76) at com.rapidminer.operator.ModelApplier.doWork(ModelApplier.java:100) at com.rapidminer.operator.Operator.execute(Operator.java:866) at com.rapidminer.operator.execution.SimpleUnitExecutor.execute(SimpleUnitExecutor.java:51) at com.rapidminer.operator.ExecutionUnit.execute(ExecutionUnit.java:711) at com.rapidminer.operator.OperatorChain.doWork(OperatorChain.java:375) at com.rapidminer.operator.Operator.execute(Operator.java:866) at com.rapidminer.Process.run(Process.java:949) at com.rapidminer.Process.run(Process.java:873) at com.rapidminer.Process.run(Process.java:832) at com.rapidminer.Process.run(Process.java:827) at com.rapidminer.Process.run(Process.java:817) at com.rapidminer.gui.ProcessThread.run(ProcessThread.java:63) I think we dont' t have community edition for Studio 6? Because when I try to update the studio it gives 400 error.

Marco_Boeck · Answer

Hi,

the real log can be found in USER_HOME/.RapidMiner5/rm.log. However I suspect that this is a bug that no longer exists in Studio 6.

Regards,
Marco

seesiva · Answer

Marco Boeck  wrote:
Hi,

you can try and add a breakpoint after the "Select Attributes" operator. Then you see the actual data coming into the "Set Role" operator. Make sure that the selected attribute does actually exist in your data. Normally it should simply tell you that the attribute does not exist, but it might be a bug that existed in RM Studio 5 and was fixed in RM Studio 6.

Regards,
Marco

This is the log I'm getting:

Aug 5, 2014 7:14:41 PM SEVERE: Here:           Process[1] (Process)
           subprocess 'Main Process'
             +- Read Database[1] (Read Database)
             +- Read CSV[1] (Read CSV)
             +- Select Attributes[1] (Select Attributes)
             +- Set Role[1] (Set Role)
             +- AdaBoost[1] (AdaBoost)
           subprocess 'Learning Process'
             |     +- Naive Bayes[10] (Naive Bayes)
       ==>   +- Apply Model[1] (Apply Model)
Aug 5, 2014 7:14:41 PM SEVERE: java.lang.NullPointerException