To analyze a dataset from banking I have both numerical and categorical values. I transform them to analyze with k-prototypes.

The original dataset:

enter image description here

The modified dataset:

  • E.g.: Job (for 1 to 12 'cos there are 12 levels)

enter image description here

Should I scale the dataset before doing the k-prototypes?

How could I determine the optimal "k" to choose (coding)?

I thought to execute:


lbd <- lambdaest(BPor)

kpres <- kproto(BPor, 5, lambda = lbd) #Change '5' for every possible value of k.


And then, calculate the sum of within cluster error (choosing the little one).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.