2

I'm usig RapidMiner for the first time. I have a dataset (in .xlsx format) on which I want to run the neural network algorithm. I am getting this error;

The operator NeuralNet does not have sufficient capabilities for the given data set; polynomial attributes not supported

Any help about this please?

Thank in advance!

enter image description here

Has QUIT--Anony-Mousse
  • 76,138
  • 12
  • 138
  • 194
user3606198
  • 97
  • 1
  • 3
  • 10
  • Please upload some of the data or show us what it looks like. Always strive for a reproducible example so that others can help you. Having said that, it looks like you have polynomial attributes and that particular operator does not support polynomial attributes. – JasonAizkalns Dec 22 '14 at 14:34
  • You may also want to talk through or show a screenshot on how you are feeding the data to the NN operator. Are you applying any other operators before the data gets to NN? Have you set a target/label variable? This question could be better for RapidMiner's own **[forum](http://forum.rapid-i.com/)** where people generally copy/paste the `XML` so that others can reproduce the error or process. – JasonAizkalns Dec 22 '14 at 14:48
  • evaluation column is the label and no operators are being applied. Thanks for the link! – user3606198 Dec 22 '14 at 14:50
  • Are you sure the error says `polynomial` and **NOT** *`polynominal`* – JasonAizkalns Dec 22 '14 at 14:58
  • Only **binary** and **numerical** attributes are supported. `high/med/low` is three different values. – Has QUIT--Anony-Mousse Dec 22 '14 at 18:11

1 Answers1

0

Per the Neural Net operator's Help file...

...This operator cannot handle polynominal attributes.

Your given input file has several binominal and polynominal attributes. Therefore, if you wish to use the out of the box Neural Net operator, you need to convert your nominal data to numerical data. One way of doing this within RapidMiner is with the Nominal to Numerical operator.

Always be cognizant of the type of data/attribute you are maniuplating: (1) text, (2) numeric, and (3) nominal.

JasonAizkalns
  • 20,243
  • 8
  • 57
  • 116