Thank you very much to all of you for the responses!
Phil, the following two examples worked well in re-categorizing. Is there
any way I can retain my original data.frame format? Once I re-categorize
the data, the format becomes numeric and the original column names are not
retained. I probably should have mentioned this earlier - I plan on using
the re-categorized data for coxph using the surv() function.
Here's how I am applying the re-categorization to my data:
*****************************************************************************
library(survival)
library(car)
gg <- read.table("k.csv", header=TRUE, sep = ",")
col = dim(genot)[2]
for(i in 1:col) {
aa<- recode(gg[,i], "c(1,2)='1'")
}
for(i in 1:col) {
dd<-factor(gg[,i],levels=0:2,labels=c('0','1','1'))
}
Thanks,
CC
On Sat, Jul 17, 2010 at 2:15 PM, Phil Spector <spec...@stat.berkeley.edu>wrote:
> Please look at Peter Dalgaard's response a little more
> carefully. There's a big difference between the levels=
> argument (which must be unique) and the labels= argument (which need not
> be). Here are two ways
> to do what you want:
>
> d = 0:2
>> factor(d,levels=0:2,labels=c('0','1','1'))
>>
> [1] 0 1 1
>
>> library(car)
>> recode(d,"c(1,2)='1'")
>>
> [1] 0 1 1
>
>
> - Phil Spector
> Statistical Computing Facility
> Department of Statistics
> UC Berkeley
> spec...@stat.berkeley.edu
>
>
>
>
--
Thanks,
CC
[[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.
