AI engineering glossary · Classical ML algorithms
What is k-means?
K-means (also called k-means clustering, Lloyd's algorithm): A clustering algorithm that splits data into k groups by alternating two steps: assign each point to its nearest centre, then move each centre to the average of its points. It repeats until assignments stop changing. It is fast but assumes roundish clusters of similar size and needs k in advance.
K-means: an example
Grouping 50,000 shoppers into k=4 segments using annual spend and visit frequency.
K-means in Python
A short example you can run (Python 3.11, NumPy, scikit-learn). The output below is what it really prints.
import numpy as np
from sklearn.cluster import KMeans
spend = np.array([[200, 2], [220, 3], [250, 2], [5000, 30], [5200, 28], [4800, 35]]) # rupees, orders
km = KMeans(n_clusters=2, n_init=10, random_state=0).fit(spend)
print(km.labels_)
print(km.cluster_centers_.round(0))Output
[1 1 1 0 0 0] [[5.00e+03 3.10e+01] [2.23e+02 2.00e+00]]
Related terms
- Centroid
- K-means++
- Elbow method
- Inertia
More Classical ML algorithms terms
Where you learn it
K-means is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.