The command executes the fuzzy c-means algorithm to divide the data set <datain> into clusters. The centroids of the clusters are stored into the data frame <dataout> and the classification information to the classified data <cldata>. The values with flag fi is the fuzzyness index and with the flag -my is the limit for membership values. The number of clusters is defined by a value with the flag -nclu.
Example (ex5.16): The example demonstrates the basic use of the command. When the clustering has been done, the operation clstat is useful to explore clusters in more details.
... NDA> load boston.dat NDA> select flds -f boston.indus boston.dis boston.crim boston.age NDA> fcm -d flds -dout clusdat -cout clucld -eps 0.0 -fi 3 -my 0.7 -nclu 4 -imax 100 NDA> clstat -c clucld -d boston -dout clusta -avg -hits -quar -name NDA> mkgrp win1 -d clusta ...