K-Means Clustering

K-MEANS groups data into K clusters by iteratively assigning points to the nearest CENTROID and updating centroids to the cluster mean.

Unsupervised — no labels needed.

Example 1 (python)

from sklearn.cluster import KMeans
k = KMeans(n_clusters=3, n_init=10, random_state=42).fit(X)
print(k.labels_[:10])

Output

[0 2 1 0 1 2 0 1 2 0]

Each point gets a cluster ID.

Example 2 (python)

# Use the elbow method to pick K

Plot inertia vs K and pick the elbow.

Key points

💡 Note: Set `n_init=10` (or higher) to avoid landing in a bad local minimum.