Reference no: EM133186573
Question: We have a dataset with 8 two-dimensional points: A = (3,1), B = (5,1), C = (4,2), D = (5,2), E = (2,5), F = (7,4), G = (1,0), H = (8,0). Use K-means and the Euclidean distance to cluster this dataset into 2 clusters.
(a) If the initial cluster centroids are at (1,2) and (1,4), what are the final clusters? Show the step-by-step calculations.
(b) If the initial cluster centroids are at (3,4) and (6,4), what are the final clusters? Show the step-by-step calculations.
(c) Between the two results from a) and b), which is a better grouping in terms of within-cluster variance? Justify your answer.