Skip to content

dperede/KMeans-Multidistance

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

KMeans-Multidistance

The traditional implementation of K-Means algorithm is usually considering only the euclidean distance to compute the distance between the points in the feature space. This new libary is an implementation of the K-Means algorithm with multiple distances choices:

  • Euclidean Distance
  • Cosine Distance
  • City-Block Distance
  • L1 Distance
  • L2 Distance
  • Manhattan Distance
  • Bray-Curtis Distance
  • Canberra Distance
  • Chebysev Distance
  • Correlation Distance
  • Mahalanobis Distance
  • Seuclidean Distance
  • Sqeuclidean Distance

Usage

In order to install the library, use pip:

pip install kmeans_multidistance

To see an introduction to using the library, please check the demo notebook Demo Notebook