MATLAB: Kmeans explanation of information obtained

classificationclusterkmeansStatistics and Machine Learning Toolbox

>> [IDK,C,sumd,D] = kmeans(B,4);

I was wondering if someone could explain to me what C, sumd, and D values where for the kmeans function. I looked at the appropriate information on mathworks however it seemed vague.

Best Answer

IDK is the indices that match each of the N rows of input into a cluster number.

C are the locations of the centroids of the k clusters, each of which will have size(B,2) components.

D returns the distance between each of the N input rows and each of the k cluster centers. So this would be pdist2(B, C)

sumd is a cluster statistic that I am unsure of the use of. Numerically it is

for K = 1 : k
  sumd(K) = sum(D(IDX == K, K));
end

that is, for each cluster, it is the sum of the distances between the points that belong to the cluster and the center of that cluster.

Related Solutions

MATLAB: How i can solve this problem? Pleas!

Your ‘T’ matrix must become a cell array. See my sample of ‘T’ for an example.

Once you do that, I would do something like this:

Y = [12.004
    13.1573 
    11.1665  
    11.8082    
    12.2129   
    12.8075   
    12.4167  
    11.5708   
    12.5798    
    13.7489];
T={'cluster2'; 'cluster1'; 'cluster3'; 'cluster9'; 'cluster0'; 'cluster7'; 'cluster4'}; % Sample Of Cell Array
[UnqClust,~,idx] = unique(T);                                                           % Unique Values & Locations
Out = Y(idx);                                                                           % Mapped Output
for k1 = 1:length(idx)
    fprintf(1, '\t%s\t%.4f\n', T{k1}, Out(k1))              % Demonstration Output (Delete Loop)
end
  cluster2  11.1665
  cluster1  13.1573
  cluster3  11.8082
  cluster9  12.4167
  cluster0  12.0040
  cluster7  12.8075
  cluster4  12.2129

MATLAB: I want solution for this problem

This code might do what you are looking for

ix = sscanf( T(:,end), '%1d' );
Y  = cat( 1, Y, rand );     % add one element to get 10
R  = Y(ix+1);

inspect the result

>> R(1:6)'
ans =
   11.1665   11.1665   11.1665   11.5740   11.5740   11.5740

where

T=['cluster2'
'cluster2'
'cluster2'
'cluster7'
'cluster7'
'etc ....'];

Best Answer

Related Solutions

MATLAB: How i can solve this problem? Pleas!

MATLAB: I want solution for this problem

Related Question