I have dataset with the shape of (1000,20) (1000 rows, 20 features) and I want to build a classifier for it. However, most sk-learn algorithms assume the these 20 features are independent. In my features, there is a gaussian dependency between the features. How can I model this dependency as an input for a classifier like SVM or ExtraTreeClassifier?


  • $\begingroup$ Could you explain what you mean by "independent" and "gaussian dependency"? The reason for asking is that extremely few methods assume all features are independent: that rare condition holds exclusively for certain kinds of experiments. Thus, although I am unfamiliar with the sk-learn algorithms, I strongly doubt many (if any at all) assume independence in the usual statistical sense. $\endgroup$ – whuber Oct 20 '19 at 20:35
  • $\begingroup$ @whuber OK , I mean that I know for certain that they are related and this dependecy can be modeled by a function; Now , my aim is to model it in order to improve classification. Does it make sense? $\endgroup$ – okuoub Oct 20 '19 at 21:10

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.