Distance Matrices: Euclidean, Manhattan & Why Scaling Comes First
This lesson is part of the course
In this lesson
You scale two store features to 0–1, build the full 12 × 12 Euclidean distance matrix and see how unscaled data lets one feature decide everything.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Distance Matrices: Euclidean, Manhattan & Why Scaling Comes First Locked
- Agglomerative Clustering: Single vs Complete Linkage, Step by Step Locked
- Reading a Dendrogram: Merge Heights, the Largest Gap & Cluster Labels Locked
- Silhouette Score per Store: a, b, s and the Average Locked
- Choosing k: Elbow Rule vs Silhouette Locked
- k-Medoids (PAM): Total Cost and One Swap Step Locked
- DBSCAN by Hand: eps, minPts and Core, Border & Noise Points Locked
- Cluster Profiling and a Scatter Chart Coloured by Cluster Locked