I have been reading the book Hands of ML of Geron and a question arose for me the PCA you do after Normalization.
- let's say u do a cross validation u do multiple PCA's, there could be a bug in some fold, e.g in a training set a feature will be removed from PCA and to other folds this feature will remain? (for modeling pca, not for scatter plot)
2)and what u do with categorical data and numeric ( I do understand is for continius variables and not for discrete)
thank you in advance