Options

A new column based on existing columns

jackuct1jackuct1 Member Posts: 3 Contributor I
edited December 2018 in Help

I want to generate a new column b based on existing column a

 

Suppose in the existing column a I have the following values

3,3,5,5,7,7,9,9

 

In the new columns, if the values is in [0,25],(25,50],(50,75],(75,100] percentile, I would have values 1,2,3,4

so for the new column b, I have values 1,1,2,2,3,3,4,4

 

How could generate this new column in rapidminer?

 

Answers

  • Options
    Fred12Fred12 Member Posts: 344 Unicorn

    you can use "Generate Data by user specification" operator, it can create new columns based on column names of an existing example set..

     

    but maybe "Generate Attributes" is more suited for you because its more flexible, you can use conditional expressions like if then.. and also reuse your old columns to create new columns..

  • Options
    Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn
    If you pivot your data first so all your data that is to be analyzed in this way is in the same attribute then you can calculate simple quartiles or other similar measures you can use "Discretize by Frequency". Note that this will replace your original attribute so you may want to Generate Copy first.
    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
Sign In or Register to comment.