a) Using agglomerative hierarchical clustering, create by hand a dendrogram for the following 10 points in one dimension:

{2.2,2.0,0.3,0.1,0.2,0.4,1.6,1.7,1.9,2.0}

While clustering, use the following similarity metric between any two clusters:

20- minxDix'Dj||x-x'||,

where represents one of the clusters and represents a different cluster. (In other words, use single-link clustering.)

b) If you were to perform k-means clustering on the same data, what would be the best number for k based on your dendrogram? Explain why you chose that value for k.