Weighting and nominal attributes
Hello there rapidminers
Small question on the process which is used for weighting attributes within auto model process.
It has a section which processes nominals, namely, performs dummy coding:
The question is, for what reason this is done specifically for weighting process?
How then one should interpret weighting results?
For example, here are results from IP traffic classification, with and without dummy coding; as one can see, for binominal categories weights are exactly the same in values, but how to interpret certain chosen values included in the first case (all false except for cat_spam = true)?
Weights with dummy codingWeights without dummy coding
(kindly tagging @IngoRM)