Hitachi Vantara Pentaho Community Forums
Results 1 to 3 of 3

Thread: Numerical and nominal

  1. #1
    Join Date
    Jun 2015
    Posts
    12

    Default Numerical and nominal

    Hello,
    I read that an algorithm as J48, for example, can work with numerical and nominal attributes. But in the examples of dataset included in the program there are datasets with either nominal or numerical attributes, not both of them in the same dataset. I mean, a column with numerical attributes and a column with nominal attributes and so one, except for the class). So, an algorithm like J48 can classify both types of data together ? And a clustering algorithm? Thank you !

  2. #2
    Join Date
    Aug 2006
    Posts
    1,741

    Default

    Yes, just about all classification and clustering schemes can accept both numeric and nominal independent attributes (at the same time). Scheme's like J48, naive Bayes, other decision trees and rule learners can handle multi-valued nominal attributes directly. In other cases, for example regression, the classifier will perform a data transformation internally, using a Weka filter, in order to convert nominal attributes into binary numeric ones (one hot encoding).

    Cheers,
    Mark.

  3. #3
    Join Date
    Jun 2015
    Posts
    12

    Default

    All right! Thank you !

Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Privacy Policy | Legal Notices | Safe Harbor Privacy Policy

Copyright © 2005 - 2019 Hitachi Vantara Corporation. All Rights Reserved.