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.

Problem With The Apply Threshold Function

SelaTheRockSelaTheRock Member Posts: 2 Learner I
in Help
So I tried to make a Logistical Regression on a data and when I run it the apply threshold gets an error saying:
"Predicted label is incompatible"
"The values of the predicted label does not match the model expectation. Value {0} unknown".

Best Answers

  • lionelderkrikorlionelderkrikor RapidMiner Certified Analyst, Member Posts: 1,195 Unicorn
    Solution Accepted
    Hi @SelaTheRock,

    In attached file, the working process...
    There was an inconsistency between the setting of classes in Create Threshold operator (Yes, No) and the expected output of the label (true/false).
    Moreover I done several modifications in your process in order to become more relevant.

    To go further, you have an highly imbalanced dataset (true = 7654 / false = 58), that 's why your logistic regression model predicts only
    the class = True.
    I think it's not what you want.
    To improve your process, you can use the Smote Upsampling operator as a preprocessing step in order to increase artificially your minority class(false). by this way you will be able to predict correctly your minority class...

    Good luck ! 

    Regards,

    Lionel
  • SelaTheRockSelaTheRock Member Posts: 2 Learner I
    Solution Accepted
    Hi @lionelderkrikor
    Thank you so much, You helped me a lot I really appreciate the quick answer.

Sign In or Register to comment.