initial.Centers {clusterSim} | R Documentation |
Function calculates initial clusters centers for k-means like alghoritms with the following alghoritm (similar to SPSS QuickCluster function)
(a) if the distance between x_k
and its closest cluster center is greater
than the distance between the two closest centers (M_m
and M_n
), then x_k
replaces either M_m
or M_n
, whichever is closer to x_k
.
(b) If x_k
does not replace a cluster initial center in (a), a second test is made:
If that distance d_q
greater than the distance between M_q
and its closest
M_i
, then x_k
replaces M_q
.
where:
M_i
- initial center of i-th cluster
x_k
- vector of k-th observation
d(...,...)
- Euclidean distance
d_{mn}
= min_{ij} d(M_i,M_j)
d_q = min_i d(x_k,M_i)
initial.Centers(x, k)
x |
matrix or dataset |
k |
number of initial cluster centers |
Numbers of objects choosen as initial cluster centers
Marek Walesiak marek.walesiak@ue.wroc.pl, Andrzej Dudek andrzej.dudek@ue.wroc.pl
Department of Econometrics and Computer Science, University of Economics, Wroclaw, Poland http://keii.ue.wroc.pl/clusterSim/
Hartigan, J. (1975), Clustering algorithms, Wiley, New York. ISBN 0-471-35645-X.
#Example 1 (numbers of objects choosen as initial cluster centers)
library(clusterSim)
data(data_ratio)
ic <- initial.Centers(data_ratio, 10)
print(ic)
#Example 2 (application with kmeans algorithm)
library(clusterSim)
data(data_ratio)
kmeans(data_ratio,data_ratio[initial.Centers(data_ratio, 10),])