K-Means Clustering

Introduction

K-means partitions points into k groups by repeatedly assigning each point to the nearest centroid and recomputing centroids as cluster means. It works well when clusters are compact and roughly spherical.

Understanding the topic

Pick k Use domain knowledge, silhouette scores, or the elbow plot of inertia vs k.

Scale first Distance-based clustering usually needs standardized features.

• Pick k — Use domain knowledge, silhouette scores, or the elbow plot of inertia vs k.
• Scale first — Distance-based clustering usually needs standardized features.

Step-by-step explanation

1. Pick k — Use domain knowledge, silhouette scores, or the elbow plot of inertia vs k.
2. Scale first — Distance-based clustering usually needs standardized features.

Informative example

Python starter:

from sklearn.cluster import KMeans
import numpy as np

X = np.array([[1, 2], [1, 4], [10, 2], [10, 4]])
labels = KMeans(n_clusters=2, random_state=0, n_init=10).fit_predict(X)
print(labels.tolist())

[1, 1, 0, 0]

Execution workflow

Best practices

• Hold out a test set before hyperparameter tuning.
• Scale numeric columns for distance-based models.
• Track multiple metrics — not accuracy alone on skewed labels.

Common mistakes

• Leaking test statistics into preprocessing fit on full data.
• Training on the same rows you report as test performance.
• Chasing complex models before a simple baseline.

Hands-on exercise

Practice:

• Cluster a 2D scatter and color by label
• Try k=2 vs k=4 on the same data

Summary

K-Means Clustering — Partition points around k centroids.