Question

Questions about clustering:

#What's the difference between Hierarchical Clustering algorithm and K-means clustering?

#How to compute the Hierarchical Clustering step-by-step (basic)?

#How to compute the Kmeans clustering step-by-step (basic)?

#each that algorithm what's the type of data that is suitable for?

Answer 1

Question#1

Hierarchical Clustering:

In Hierarchical clustering we have an advantage of creating  hierarchical decomposition of the set of data that has been given to us. We can also  create hierarchical decomposition in two ways one way is to creating from  bottom to the top and the other is top to down. Where as in

K-Mean Clustering:

As the K-mean clustering is the process of making the partion of the set of data objects into subsets and in k mean clustering every subset is a cluster and it is also similar to the cluster that is greater and but the similarity between these clusters is less.

Question#2

• In the start first we will assign all the points to an individual cluster
• Now we will now look for the smallest distance that is been located in the proximity matrix and then merge those points with the smallest distance.
• Then repeat the step 2 until only a single cluster is left.

Question#3

• Assign k a value and make the intial clsuter object of that
• The assign each point a similar center
• Then identify cluster centroids
• Reassign the points
• Identify the new cluster centorids

Question#4

In all these algorithms the type of data is been required is that the data point should classigy the  the distance between that points

PLEASE GIVE A THUMBS UP!!!!!!!!!!