r2cluster {ctc} | R Documentation |
Converting data to Cluster format
r2cluster(data,labels=FALSE,colname="ACC",description=FALSE, file="cluster.txt",dec='.')
file |
the path of the file |
data |
a matrix (or data frame) which provides the data to put into the file |
labels |
a logical value indicating whether we use the frist column as labels (ACC column in cluster file) |
colname |
a character string indicating what kind of objects are in each row. YORF, MCLID, CLID, ACC can be used: see details. |
description |
a logical value indicating whether we use the second column as description (NAME column for cluster file) |
dec |
the character used in the file for decimal points |
Software Cluster, made by M. Eisen needs formatted input data like:
ACC NAME GWEIGHT GORDER V3 V4 V5 EWEIGHT 1 1 1 gbk01 Gene1 1 1 0.9 0.4 1.4 gbk02 Gene2 1 2 0.6 0.2 0.2 gbk03 Gene3 1 3 1.6 1.1 0.9 gbk04 Gene4 1 4 0.4 1 1
First field of first line (i.e "ACC") is a special field, that tells program what kind of objects are in each row.
Four special values are defined with web link (when visualize with TreeView):
Line begining with EWEIGHT
gives weights for each
column (variable). Column GWEIGHT
gives weights for each line
(individuals).
Cluster is a program made by M. Eisen that performs hierarchical clustering, K-means and SOM.
Cluster is copyrighted. To get or have information about Cluster: http://rana.lbl.gov/EisenSoftware.htm
Antoine Lucas, http://antoinelucas.free.fr/ctc
Antoine Lucas and Sylvain Jasson, Using amap and ctc Packages for Huge Clustering, R News, 2006, vol 6, issue 5 pages 58-60.
# Create data set.seed(1) m <- matrix(rep(1,3*24),ncol=3) m[9:16,3] <- 3 ; m[17:24,] <- 3 #create 3 groups m <- m+rnorm(24*3,0,0.5) #add noise m <- floor(10*m)/10 #just one digits r2cluster(m)