RapidMiner: The input Exampleset does not match the training ExampleSet. Missing Attribute: aaa.

In case you are working with separate data sets for training and testing and want to do some text mining, you probably get this error message:

"The input Exampleset does not match the training ExampleSet. Missing Attribute: "aaa".

What does it mean? Well, you input data sets whose feature vectors differ. It is quite easy to explain. If you have two texts, the probability that both contain exactly the same words converges to zero. And if you have different words and apply a tokenizer, you will get different feature vectors.

There is a simple workaround. Each "Process Documents" operator have an output called "wor". You just have to connect this output to the "Process Documents" operator which handles your other data set. 

RapidMiner: Attributes do not match

Leave a Comment

comments powered by Disqus