Options

Augmentation Randomization/Multiply

Sunnyboy_nhSunnyboy_nh Member Posts: 10 Newbie
in Help
Any ideas how can I do a randomization with multiply or any way to the an augmentation with my dataset which only has 170 rows ?

The reason is that I need to do a split-test- validation and my dataset ist not big enough for that purpose!

Answers

  • Options
    Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn
    I would recommend exploring weighting as a solution to imbalanced, small datasets.  The other alternative is to us one of the upsampling operators from one of the free extensions.
    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
  • Options
    MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,507 RM Data Scientist
    Another way is to use the Build Simulation operator, which is part of Operator Toolbox.

    Cheers,
    Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • Options
    Sunnyboy_nhSunnyboy_nh Member Posts: 10 Newbie
    Thanks Martin and Telcontar120 for your feedbacks and suggestions. Meanwhile I have looked at a similar operator in Rapidminer called  Sample(Bootstaping) before Split Data Operator does that data augmentation by  copying the exisiting rows.
    Nevertheless I will try to check your suggestions as well :) 
Sign In or Register to comment.