Options
[SOLVED] Information Gain Feature Selection with Integer Values
Hello,
I'm using Information Gain as a method for feature selection.
The features represent the number of occurrence of a term in a document tf(t,d).
My doubt is:
In order to calculate the IG does the method implemented in RapidMiner
takes in consideration all the possible values of a feature
or only the presence or absence of a feature in a certain example?
Thanks in Advance,
Rui Vaz
I'm using Information Gain as a method for feature selection.
The features represent the number of occurrence of a term in a document tf(t,d).
My doubt is:
In order to calculate the IG does the method implemented in RapidMiner
takes in consideration all the possible values of a feature
or only the presence or absence of a feature in a certain example?
Thanks in Advance,
Rui Vaz
0
Answers