Unsupervised Learning with K-Means

When there are no labels

Clustering finds structure without answers. K-means partitions data into k groups by minimizing distance to each group's center.

from sklearn.cluster import KMeans
km = KMeans(n_clusters=4, n_init="auto", random_state=42)
labels = km.fit_predict(X_scaled)

Practical tips

• Scale your features first — k-means uses distances.
• Choosing k: try the elbow method or silhouette score.
• It assumes round, similar-sized clusters; for odd shapes consider DBSCAN.

Common uses: customer segmentation, grouping documents, and exploratory analysis.