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.

Discriminant Analysis

smajumdarsmajumdar Member Posts: 2 Learner II
edited December 2018 in Help

I wish to understand the output (from model port) of both LDA & QDA (Linear and Quadratic Discriminant Analysis) operators. When running on a small dataset (1 binomial label & 2 real number predictors), I'd expect some kind of coefficients but I get only apriori probabilities of the 2 groups represented by the binomial label. Am I missing something?

QDA.png 40.2K

Answers

  • rfuentealbarfuentealba RapidMiner Certified Analyst, Member, University Professor Posts: 568 Unicorn
    Hey @smajumdar, do you mind to share your XML process with us? Both LDA and QDA have two ports, and you have only one connected which is the mod port. Perhaps you want to see your data? For that there is the exa port but I don't see that in your picture.
  • rfuentealbarfuentealba RapidMiner Certified Analyst, Member, University Professor Posts: 568 Unicorn
    Duh me! I forgot something too! Here is a full example of applying Quadratic Discriminant Analysis on my favourite dataset: the Titanic.



    You are getting the model, but to get real insights, you should apply that model to some more data. In my case, once I apply the model on my unlabeled data, I get the "Survived" column as a prediction based in QDA.



    Please find the example attached.

    Hopefully this helps you solving your issues. Enjoy!

    Rodrigo.
  • smajumdarsmajumdar Member Posts: 2 Learner II
    Thanks buddy
Sign In or Register to comment.