Hi Fellow R enthusiasts
I have managed to reshape my data using a much shorter script than before.
Woohoo
However now I have new problems. The code is below. There are no problems with
the create matrix section.
The problem code is highlighted in bold. I am trying to do PCA on the data.
Here are the errors.
Error1
code : OGSscaled = rangescale(OGS)
error message : Error in dim(newX) <- c(prod(d.call), d2) :
dims [product 47960] do not match the length of object [43600]
Error2
I tried to do PCA without rangescaling
code :OGSpca <- prcomp(OGS, center=FALSE)
error message : Error in svd(x, nu = 0) : infinite or missing values in
'x'
CODE
######################################################
########### Create matrix ###########################
######################################################
# load packages
require(reshape)
source("rangescale.r")
#Open the csv file
OGSdata <- read.table("MG3199.csv",sep=",",header=TRUE)
#create matrix
x.m <- melt(OGSdata, measure.var="pct")
OGS <- cast(x.m, mci ~ sample)
######################################################
########### PCA ####################################
######################################################
#scale profiles
OGSscaled = rangescale(OGS)
#do PCA
result = prcomp(OGS, center=FALSE)
#obtain scores matrix
scores=result$rotation
#PC1 vs PC2 plot
plot(scores[,1], scores[,2], xlab="PC1", ylab="PC2")
#add labels (0.005 and 0.003 offset to aviod obscuring points
Kind Regards
Amit Patel
___________________________________________________________
now.
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
