In Rapidminer, as soon as I import a dataset, how do I change the column type?

Question

I imported datset into Rapidminer 5, and one of the columns, which was supposed to be nominal or polynomial, was set to numeric. There are more than 500 attributes in my dataset, so I don’t want to make a reimport error every time I realized that I made a mistake. Is there a way to automate the import process so that it saves the types of columns that I set each time, or can I go back and edit the already imported attribute types of the dataset?

Answer 1

add this statement to your process after loading the data:

Data Conversion> Type Conversion> Numeric Value in Polynomial

on the operator, select

attribute type filter = single
attribute = [name of your attribute]

Answer 2

here you go: http://i.stack.imgur.com/ov5yn.png

• Select Numeric for Polynomial
  • Then change the " attribute filter type " to " subset ". Then select the attributes you want to change.
  • Another suggestion: it’s better to save this output in your local repository so that you don’t need to convert every time you need data. This way you will have both the original and the duplicate in your basket. :)
  • Happy data mining ...

Answer 3

apply the "set role function" function:

It is specified in statements -> data transformation -> Role name and modification -> Set role