Implement K-Means Clustering

Coding: Implement K-Means Clustering Given n data points in d dimensions and a target number of clusters k, implement K-Means and output the cluster label for each point. Input (stdin) Line 1: three integers n d k Next n lines: d floating-point numbers per line representing a point Last line: two numbers max_iter tol Output (stdout) Print n lines. Line i contains the cluster label (from 0 to k-1) assigned to point i. Constraints 1 <= n <= 2000 1 <= d <= 20 1 <= k <= min(n, 50) 1 <= max_iter <= 200 tol >= 0 is the convergence threshold: stop if the maximum centroid movement between two iterations is <= tol. Requirements Initialization: use the first k points as initial centroids. Assignment: assign each point to the nearest centroid by Euclidean distance; break ties by choosing the smallest cluster id. Update: each centroid becomes the mean of points assigned to it. Empty cluster: if a cluster gets no points, keep its centroid unchanged. Test cases See tests below. Example Input 6 2 2 0 0 0 1 1 0 10 10 10 11 11 10 100 0 Output 0 0 0 1 1 1