🎉 🎉 RAPIDMINER 9.10 BETA IS OUT!!! 🎉🎉

GRAB THE HOTTEST NEW BETA OF AI HUB/SERVER, STUDIO, AND RADOOP. LET US KNOW WHAT YOU THINK!

CLICK HERE TO DOWNLOAD

Need guidance for Modeling and Preparation Datasets is given

AtillaAtilla Member Posts: 8 Newbie
edited June 17 in Help
Dear Community,

just started to get confi with rapidminer (absolute beginner)
I´ve tried to build a process mainly focused on labeling target attribute, detecting outliers, missing values.
In the end I should be able to build a model which can predict wine quality
therefore I need to build a baseline classification with training and test data
The modell should be improved in the end and evaluated

I am really stuck in the preparation process.
For further details please have a look at my processes and lecture sheet.

I would be greatefull for any hint or guidance

Best regards
Atilla

Best Answers

  • ceaperezceaperez Member Posts: 195   Unicorn
    Solution Accepted
    I review your process. there are some redundant operators but in general good work. I don't know where are you stuck. you removed the noise, missing values and reduced the label to three values. 

    Best
    Atilla
  • AtillaAtilla Member Posts: 8 Newbie
    Solution Accepted
    Thank´s for your review I apprecite it. Now I finished it with modelling and testing. Would you keen to have a look on that process? Are they mistakes or redundancies?

    Kindley Regards

  • ceaperezceaperez Member Posts: 195   Unicorn
    Solution Accepted
    Hi @Atilla

    Without the excel file I can't run the process. however, looking at process I can see that you are using a Select Attributes operator and you are selecting all of them, It's no necessary. also you are using a Set Role Operator, after Select Attributes, with the label attribute but assigning it a regular role, for then assigning it a label label role into the Cross Validation Operator. you can remove the first Set Role Operator

    Best
    Atilla
  • AtillaAtilla Member Posts: 8 Newbie
    Solution Accepted
    Awesome thank you. By the way, here are the excell files.

Answers

Sign In or Register to comment.