My data contains about 150 water extraction events (some features are mean flow rate, duration etc.) from toilets, showers, washing machines, taps etc. I want to use a classifier which is able to predict if an event is a toilet or not. Therefore, I have a binary classifier in mind (class 1 represents the toilet, 0 represents the rest).

I thought of logistic regression or linear discriminant analysis, but I am not sure if that would be best. In case of logistic regression I am not sure if the amount of toilets (about 25) is enough and in case of LDA although toilets observations can be considered to be drawn from a Gaussian distribution, all remaining types of fixtures are definitely not drawn from such a distribution and would be part of the 0 class of a binary classifier.

Which classification method would you take into consideration to use? Or how would evaluate which methods fits best?

  • 2
    $\begingroup$ Please note logistic is not a classifier. $\endgroup$ – SmallChess May 4 '17 at 13:28

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.