how can i calculate entropy and standard deviation of one numeric feature for each record?

ramzanzadeh72ramzanzadeh72 Member Posts: 14 Contributor I
edited November 2018 in Help

hi

i am new in rapidminer and i want to calculate entropy and standard deviation of one feature for each record of example set... i cant find this operator.... how i can do it????

 

 

Tagged:

Answers

  • sgenzersgenzer 12Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,448  Community Manager

    hello @ramzanzadeh72 - welcome to the community. I'm confused with your question. How do you calculate the standard deviation of only one number? If you want to calculate the standard deviation of an entire column/feature, you can do this easily with the Aggregate operator.


    Scott

     

  • ramzanzadeh72ramzanzadeh72 Member Posts: 14 Contributor I

    yes, actually i want to calculate entropy and standard deviation of one feature for entire records... standard devation can be calculate by "aggregate operator" but what about entropy???

  • sgenzersgenzer 12Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,448  Community Manager

    hmm I have never heard this request before. IFAIK the only way to do this would be to compute the formula with a Generate Macro operator.

     

    Scott

     

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761   Unicorn

    @ramzanzadeh72 I assume you are referring to Information theory. So there's a few ways to do it. There's an operator called Discretize by Entropy and there is are some weighting operators using Information Gain. 

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761   Unicorn
Sign In or Register to comment.