search

nicodv / kmodes

Python implementations of the k-modes and k-prototypes clustering algorithms, for clustering categorical data
MIT License
1.23k stars 416 forks source link

Performance over binary data #172

Closed ale94mleon closed 2 years ago

ale94mleon commented 2 years ago

I need to cluster binary vectors, I am currently using kmodes. I have been consulting the bibliography and there are a zoo of methods for categorical data classification and Kmodes is one of the most recommended. My question: Is kmodes still good for binary data, is there some review (paper) for documentation on this? In some how binary data is categorical data, but I am still a little confuse after been reading for a whole day about clustering :-\ Thank you so much for any feedback.

nicodv commented 2 years ago

This is a very broad, theoretical question that is way outside the scope of the kmodes issue tracker, hence closing.

I think you can use kmodes without any problem, but I can't weigh in on whether it's the best choice for your particular data set and use case.