Skip to content

Need help with output of Proximus algorithm

1 message · Matej Zuzčák

Original
Matej Zuzčák
# 
Hello list members,

I have question about output of PROXIMUS algorithm. In the example of
use here:
https://en.wikibooks.org/wiki/Data_Mining_Algorithms_In_R/Clustering/Proximus#Algorithm
in Case Study section is all clear, but I do not know what way they use
for get clustered words to groups: Group 1 (computers) = {intel,
computer, software, linux, windows, Firefox, explorer, programming}
Group 2 (authors) = {kuth, shakespeare, grisham, asimov, book} Group 3
(noise) = {love}. How can I get this output for my data please? Next in
the example section is graph. How do I read this graph please?

My data are:

objects cat1    cat2    cat3    cat4 ...
A       TRUE    FALSE   FALSE   FALSE
B       TRUE    FALSE   TRUE    FALSE
C       TRUE    FALSE   FALSE   FALSE
D       FALSE   TRUE    TRUE    TRUE
E       TRUE    TRUE    TRUE    TRUE
F       TRUE    FALSE   TRUE    FALSE

After apply of Proximus algorithm I get this output:
Non-Zero: 55
Sparsity: 0.48
  0 [6,3,5] 1 >
  1 [3,3,5] 1 * 1
  1 [3,1,0] 1 >
  2 [1,1,0] 1 * 2
  2 [2,1,0] 1 >
  3 [1,1,0] 1 * 3
  3 [1,1,0] 1 * 4
  2 <
  1 <
  0 <
Size Length Radius Error Fnorm Jsim Valid
1    3     16      5  0.16     3 0.81  TRUE
2    1      9      0  0.00     0 1.00  TRUE
3    1      4      0  0.00     0 1.00  TRUE
4    1      2      0  0.00     0 1.00  TRUE

So it means that 3 objects are in one cluster and all other objects have
own cluster. What way I can use for get list of objects in cluster
please? And I get this graph (see in attachment). How do I read this
graph please? 

Many thanks for your help!