πŸŽ‰ πŸŽ‰ RAPIDMINER 9.10 IS OUT!!! πŸŽ‰πŸŽ‰

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

Decision tree

desaijayantidesaijayanti Member Posts: 1 Contributor I
edited November 2018 in Help
Hello! We are trying to create a Decision tree for a sample data using RapidMiner. The data contains 10 columns. However, the decision tree is categorising based on only one column. Is there any change in the settings which has to be done? If so can someone please let us know? Thanks in advance!!

Best Answer

  • RalfKlinkenbergRalfKlinkenberg Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, RMResearcher, Member, Unconfirmed, University Professor Posts: 68  RM Founder
    Solution Accepted
    Deactivating pruning and pre-pruning can help.
    Setting the "minimal gain" parameter of the decision tree learner to a smaller value, e.g. 0.05 or 0.01 usually helps as well.

Answers

  • Marco_BoeckMarco_Boeck Team Lead Software Engineering Administrator, Moderator, Employee, Member, University Professor Posts: 1,963   RM Engineering
    Hi,

    can you please post your process XML ("View" -> "Show View" -> "XML")? Ideally you also include a link to your data. My guess would be that "minimal gain" or "min leaf size" or "minimal size for split" parameters might be responsible.

    Regards,
    Marco
Sign In or Register to comment.