"Similarity Measure into Clustering"

Question

Hi Guys,

Is it possible to use RM to create a distance matrix (say Jaccard Sim) and use this matrix into a cluster analysis? If so are there any examples?

Thanks!

Brian

land · Answer

Hi,
K-Means does always use Euclidean distance, it's simply part of the algorithm. In Kmedoids, you might select the distance function, but you cannot forward a similarity matrix. It will calculate the similarities from the given example set as it needs them.

Greetings,
  Sebastian

B_Miner · Answer

Hi Sebastian, I tried to hook up a Data to Similarity operator to kmeans and got an error. Is kMedoids the only clustering that can take a distance matrix as input? Example that causes error for type of input into kmeans:

land · Answer

Hi Brian,
both is possible. You might create a distance matrix using the Data to Similarity operator and select Jaccard Simularity as distance function. And you might do clustering selecting the same distance function using for example kMedoids.

Greetings,
  Sebastian