I have a question about the functioning of PCA. I have a dataset with only 2 categorical attributes out of 9. Is it good to calculate pca between those two? Does it help me understanding anything special? here's my dataset


  • $\begingroup$ What do you mean by PCA between those two? PCA is a way to understand the structure of the data as a whole, not necessarily about inner relationships $\endgroup$ – Valentin Calomme May 8 at 11:37
  • $\begingroup$ I'm sorry, I'm still learning and I haven't clear ideas about it... But thanks for answering me :) $\endgroup$ – user96624 May 15 at 10:06

PCA is not recommended for categorical features. There are equivalent algorithms for categorical features like CATPCA and MCA.

Decision tree for dimensionality reduction based on data types

| improve this answer | |
  • $\begingroup$ Thank you very much @Rusoiba!!! Now it's clear! $\endgroup$ – user96624 May 15 at 10:07

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.