Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

Decision Tree Operator - C5 or C4.5 algorithm?

cwerningcwerning Member Posts: 10 Contributor II
edited November 2018 in Help

Hello experts,

 

does RM still uses the C4.5 algorithm for his decision tree operator? I found some really old topics that say it uses the C4.5 algorithm.

 

Kind regards,

 

Christopher

Best Answer

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,528 RM Data Scientist
    Solution Accepted

    The shipped descion tree is actually a own implemtation. I am not sure if it follows any direct implementation, i think it is some mixture, but I am not sure.

     

    If you want to have C4.5 you may have a look on W-J48.

     

    ~Martin

     

    Edit: Just looked it up:

     * <p>
    * This operator learns decision trees from both nominal and numerical data. Decision trees are
    * powerful classification methods which often can also easily be understood. This decision tree
    * learner works similar to Quinlan's C4.5 or CART.
    * </p>
    *
    * <p>
    * The actual type of the tree is determined by the criterion, e.g. using gain_ratio or Gini for
    * CART / C4.5.
    * </p>
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany

Answers

  • cwerningcwerning Member Posts: 10 Contributor II

    Hi Martin,

     

    thank your very much for your help! But where did you found the information? Is it from a public source which I dond know? I can not find the information in operators manual.

     

    Kind regards,

    Christopher

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,528 RM Data Scientist

    Dear Christopher,

     

    i copied it from the source code. It is available at https://github.com/rapidminer/rapidminer-studio/blob/master/src/main/java/com/rapidminer/operator/learner/tree/ParallelDecisionTreeLearner.java . Im a bit unsure where this comment pops up in studio.

     

    ~Martin

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • Telcontar120Telcontar120 RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn

    If you get the Weka extension (which is free and highly recommended, since it has over a hundred predictive modeling operators) then you will have access to several different flavors of decision tree operators, including the weka implementation of the C4.5 algorithm in the W-J48 operator.

    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
  • Fred12Fred12 Member Posts: 344 Unicorn

    so I guess the C5.0 is not yet implemented in Rapidminer?

  • accounting1100accounting1100 Member Posts: 1 Learner III

    Hi

     

    Where can i find C5 in Rapid Miner? It's not in the decision tree section?

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

    You'll need to download the Weka extension to get it. 

  • Fred12Fred12 Member Posts: 344 Unicorn

    but I think C5.0 is too new and still under license to be implemented in rapidminer or weka yet, is that true?

    its only C4.5 in Weka I think...

  • thatharpandi199thatharpandi199 Member Posts: 1 Learner II

    I am Thathar

    shall I use C4.5 algorithm in Rapidminer?

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager

    hello @thatharpandi199 - I would use the normal Decision Tree operator in Studio Core. It is the best by far. :)


    Scott

     

Sign In or Register to comment.