Numerical Data Not Supported

tcm5026tcm5026 Member Posts: 5 Contributor II
edited July 2019 in Help
I am trying to learn a couple of different methods for a numerical label. 

I keep getting the error,

Error in: KernelNaiveBayes (KernelNaiveBayes) This learning scheme does not have sufficient capabilities for the given data set: numerical label not supported Each learning scheme has particular capabilities for data set handling. For example, some learners can only handle numerical attributes and can not learn from nominal attributes. Please perform a preprocessing step to transform your data set or use an alternative learning scheme. In case of a polynominal label attribute, i.e. a classification task with more than two classes, you can use a learning scheme capable only for binominal classes by wrapping a Binary2MultiClassLearner around the learning operator.

I have tried multiple different configurations of preprocessing the dataset with Binary2MultiClassLearner and other discretizations but each time I continue to get the error for numerical data.  Can someone show the right configuration of how to "wrap a Binary2MultiClassLearner" around a learning operator?

My current configuration (without an attempt at a wrapper) is,

- root


  • Options
    landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    the problem is, that if you have a numerical label, you are trying to make a regression. You aren't trying to assign the examples to a finite set of classes, instead you are predicting a continuous number like 5 or 4,634. Some operators don't support this type of task, and NaiveBayes is one of the classification only operators. Even if you wrap it inside a Binary2Multiclass operator, it won't work, since you don't have any classes!
    You must use a regression operator instead, for example the LinearRegression, SVM or NeuralNets.

    Anyway I would suggest switching to 5.0, because it will help you detect such problems.

Sign In or Register to comment.