It is well known that when you do feature selection, there are statistical tools for comparing features of the same type if you know the output, for example

  1. Numerical data - > numerical output: Pearson's correlation coefficient /Spearman's rank coefficient
  2. Numerical data - > categorical output: anova/kendall's rank coefficient
  3. Categorical data->numerical output: anova/kendall's rank coefficient
  4. Categorical data-> categorical output: Chi squared / mutual information

but in ML you very commonly have mixtures of categorical and numerical features. How do you pick one group of categorical and numerical values from a large group of features?

Also how would you do feature extraction on mixed data?



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.