0
2.7kviews
Use Data set in Appendix A. Create Adjacency Matrix. Use Single Link OR Complete Link Algorithm to Cluster given data set by drawing Dendogram.

enter image description here

This question appears in Mumbai University > Data Warehouse and Mining subject

Marks: 10 M

Year: Dec 2014

1 Answer
0
50views

Step 1: Identify the two clusters with the shortest distance in the matrix, and merge them together. Re-compute the distance matrix, as those two clusters are now in a single cluster.

enter image description here

By looking at the distance matrix above, we see the C and E have the smallest distance from all. So, we merge those two in a single cluster, and re-compute the distance matrix.

enter image description here

Distance matrix:

dist ((C,E),A)=min(dist(C,A),dist(E,A))

=min (1.41, 1.58)

=1.41

dist ((C,E),B) = min(dist(C,B),dist(E,B))

=min (2.23, 2.12)

=2.12

dist ((C,E),D) = min(dist(C,D),dist(E,D))

=min (2, 1.58)

=1.58

enter image description here

Step2: Consider the distance matrix obtained in step1. Since A,B distance is minimum, we combine A and B.

enter image description here

Distance Matrix:

dist ((A,B),(C,E)) =min(dist(A,(C,E)),dist(B,(C, E)))

=min (1.41, 2.12)

= 1.41

dist ((A,B),D) = min(dist(A,D),dist(B,D))

=min (1.41, 1)

=1

enter image description here

Step 3: Consider the distance matrix obtained in step2. Since (A,B) and D distance is minimum, we combine them.

enter image description here

dist ((C,E),(A,B,D)) =min(dist(C,A),dist(C,B), dist(C,D), dist(E,A), dist(E,B), dist(E,D))

=min (1.41, 2.23, 2, 1.58, 2.12, 1.58)

= 1.41

Step 4: Finally combine (C,E) and (A,B,D)

Final Dendrogram

enter image description here

Please log in to add an answer.