Implement K-Means From Scratch | Dataford Interview Questions

Implement K-Means from scratch.

Use PostgreSQL to cluster two-dimensional points into eight clusters. Run exactly three assignment and centroid-update iterations using the provided initial centroids. Exclude points with a NULL coordinate and resolve equal-distance assignments by choosing the lowest centroid ID.

Output

One row per valid point, with point_id, cluster_id, and distance_squared
Sort by cluster_id, then point_id
Round distance_squared to six decimal places

Schema

points

Column	Type	Description
point_idPK	INT	Unique point identifier
x	NUMERIC(10,4)	First coordinate
y	NUMERIC(10,4)	Second coordinate

initial_centroids

Column	Type	Description
centroid_idPK	INT	Unique initial centroid identifier
x	NUMERIC(10,4)	Initial centroid x-coordinate
y	NUMERIC(10,4)	Initial centroid y-coordinate

Your question is Implement K-Means From Scratch. Start with the requirements and the two tables in the Question tab.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.

Problem