k-means clustering algorithm implementation written in Go
Switch branches/tags
Clone or download
Latest commit e36119f Oct 28, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
examples Simplify colorpalette's example code Jun 5, 2018
.gitignore Initial commit May 26, 2018
.travis.yml Bump Go versions Oct 30, 2018
LICENSE Initial commit May 26, 2018
kmeans.gif Updated README and added animation May 26, 2018
kmeans.go Ensure another iteration after randomly assigning a point to a cluster Jun 5, 2018
kmeans_test.go Made randomSeed a const for tests Jun 5, 2018



k-means clustering algorithm implementation written in Go

What It Does

k-means clustering partitions a multi-dimensional data set into k clusters, where each data point belongs to the cluster with the nearest mean, serving as a prototype of the cluster.

kmeans animation

When Should I Use It?

  • When you have numeric, multi-dimensional data sets
  • You don't have labels for your data
  • You know exactly how many clusters you want to partition your data into


import (

// set up a random two-dimensional data set (float64 values between 0.0 and 1.0)
var d clusters.Observations
for x := 0; x < 1024; x++ {
	d = append(d, clusters.Coordinates{

// Partition the data points into 16 clusters
km := kmeans.New()
clusters, err := km.Partition(d, 16)

for _, c := range clusters {
	fmt.Printf("Centered at x: %.2f y: %.2f\n", c.Center[0], c.Center[1])
	fmt.Printf("Matching data points: %+v\n\n", c.Observations)


If k (the amount of clusters) and d (the dimensions) are fixed, the problem can be exactly solved in time O(ndk+1), where n is the number of entities to be clustered.

The running time of the algorithm is O(nkdi), where n is the number of d-dimensional vectors, k the number of clusters and i the number of iterations needed until convergence. On data that does have a clustering structure, the number of iterations until convergence is often small, and results only improve slightly after the first dozen iterations. The algorithm is therefore often considered to be of "linear" complexity in practice, although it is in the worst case superpolynomial when performed until convergence.


You can greatly reduce the running time by adjusting the required delta threshold. With the following options the algorithm finishes when less than 5% of the data points shifted their cluster assignment in the last iteration:

km, err := kmeans.NewWithOptions(0.05, nil)

The default setting for the delta threshold is 0.01 (1%).

If you are working with two-dimensional data sets, kmeans can generate beautiful graphs (like the one above) for each iteration of the algorithm:

km, err := kmeans.NewWithOptions(0.01, kmeans.SimplePlotter{})

Careful: this will generate PNGs in your current working directory.

You can write your own plotters by implementing the kmeans.Plotter interface.


GoDoc Build Status Coverage Status Go ReportCard