R help - Sep 2008 - Splitting row names up and then adding up the columns associated with criteria from the parts of the site coding (help)

d <- c("upwd1201", "upwd0502", "upwd0702",
"upwd1002", "upwd1102",
"upwd0203", "upwd0503", "upwd0803",
"upwd0104", "upwd0704", "upwd0804",
"upwd1204", "upwd0805", "upwd1005",
"upwd0106", "dnwd1201", "dnwd0502",
"dnwd0702", "dnwd1002", "dnwd1102",
"dnwd1202", "dnwd0103", "dnwd0203",
"dnwd0303", "dnwd0403", "dnwd0503",
"dnwd0803", "dnwd0104", "dnwd0704",
"dnwd0804", "dnwd1204", "dnwd0805",
"dnwd1005", "dnwd0106", "uppl0502",
"uppl0702", "uppl1002", "uppl1102",
"uppl0203", "uppl0503", "uppl0803",
"uppl0104", "uppl0804", "uppl1204",
"uppl0805", "uppl1005", "uppl0106",
"dnpl0502", "dnpl0702", "dnpl1002",
"dnpl1102", "dnpl1202", "dnpl0103",
"dnpl0203", "dnpl0403", "dnpl0503",
"dnpl0803", "dnpl0104", "dnpl0704",
"dnpl0804", "dnpl1204", "dnpl0805",
"dnpl1005", "dnpl0106", "uplp1201",
"uplp0502", "uplp0702", "uplp1002",
"uplp1102", "uplp0203", "uplp0503",
"uplp0803", "uplp0104", "uplp0704",
"uplp0804", "uplp1204", "uplp0805",
"uplp1005", "uplp0106", "dnlp1201",
"dnlp0502", "dnlp0702", "dnlp1002",
"dnlp1102", "dnlp1202", "dnlp0103",
"dnlp0203", "dnlp0303", "dnlp0403",
"dnlp0503", "dnlp0803", "dnlp0104",
"dnlp0704", "dnpt0804", "dnlp1204",
"dnlp0805", "dnlp1005", "dnlp0106",
"uprk1201", "uprk0502", "uprk0702",
"uprk1002", "uprk1102", "uprk0203",
"uprk0503", "uprk0803", "uprk0104",
"uprk0704", "uprk0804", "uprk1204",
"uprk0805", "uprk1005", "uprk0106",
"dnrk0502", "dnrk0702", "dnrk1002",
"dnrk1102", "dnrk1202", "dnrk0103",
"dnrk0203", "dnrk0303", "dnrk0403",
"dnrk0503", "dnrk0803", "dnrk0104",
"dnrk0704", "dnrk0804", "dnrk1204",
"dnrk0805", "dnrk1005", "dnrk0106",
"uprt1201", "uprt0502", "uprt0702",
"uprt1002", "uprt1102", "uprt0203",
"uprt0503", "uprt0803", "uprt0104",
"uprt0704", "uprt0804", "uprt1204",
"uprt0805", "uprt1005", "uprt0106",
"dnrt1201", "dnrt0502", "dnrt0702",
"dnrt1002", "dnrt0403", "dnrt0803",
"dnrt0104", "dnpt0704", "dnrt0804",
"dnrt0805", "dnrt1005", "dnrt0106",
"upsd1201", "upsd0502", "upsd0702",
"upsd1002", "upsd1102", "upsd0203",
"upsd0503", "upsd0803", "upsd0104",
"upsd0704", "upsd0804", "upsd1204",
"upsd0805", "upsd1005", "upsd0106",
"dnsd1201", "dnsd0502", "dnsd0702",
"dnsd1002", "dnsd1102", "dnsd1202",
"dnsd0103", "dnsd0203", "dnsd0303",
"dnsd0403", "dnsd0503", "dnsd0803",
"dnsd0104", "dnsd0704", "dnsd0804",
"dnsd1204", "dnsd0805", "dnsd1005",
"dnsd0106")

these are the rownames of a dataframe, and I would like to split them
up into chunks of two letters, two letter, and then the four numbers.
The problem that I am trying to solve is to add the numbers in the
columns (unique counts of species) that correspond to a "whole sample"
:

a whole sample consists of one of "1" all six of "2" for a
particular date "3"

1
up= unrestored
down=restored

2
habitat types
sd
rk
rt
pl
lp
wd

3
date - self explanitory

strsplit looks promising, but I don't know what a regular expression
is or how to use it for that matter
-- 
Stephen Sefick
Research Scientist
Southeastern Natural Sciences Academy

Let's not spend our time and resources thinking about things that are
so little or so large that all they really do for us is puff us up and
make us feel like gods. We are mammals, and have not exhausted the
annoying little problems of being mammals.

	-K. Mullis

Try this:

library(gsubfn)
do.call(rbind, strapply(d, "[a-z]{2}|[0-9]{4}"))


On Wed, Sep 24, 2008 at 9:47 PM, stephen sefick <ssefick at gmail.com>
wrote:
> d <- c("upwd1201", "upwd0502", "upwd0702",
"upwd1002", "upwd1102",
> "upwd0203", "upwd0503", "upwd0803",
"upwd0104", "upwd0704", "upwd0804",
> "upwd1204", "upwd0805", "upwd1005",
"upwd0106", "dnwd1201", "dnwd0502",
> "dnwd0702", "dnwd1002", "dnwd1102",
"dnwd1202", "dnwd0103", "dnwd0203",
> "dnwd0303", "dnwd0403", "dnwd0503",
"dnwd0803", "dnwd0104", "dnwd0704",
> "dnwd0804", "dnwd1204", "dnwd0805",
"dnwd1005", "dnwd0106", "uppl0502",
> "uppl0702", "uppl1002", "uppl1102",
"uppl0203", "uppl0503", "uppl0803",
> "uppl0104", "uppl0804", "uppl1204",
"uppl0805", "uppl1005", "uppl0106",
> "dnpl0502", "dnpl0702", "dnpl1002",
"dnpl1102", "dnpl1202", "dnpl0103",
> "dnpl0203", "dnpl0403", "dnpl0503",
"dnpl0803", "dnpl0104", "dnpl0704",
> "dnpl0804", "dnpl1204", "dnpl0805",
"dnpl1005", "dnpl0106", "uplp1201",
> "uplp0502", "uplp0702", "uplp1002",
"uplp1102", "uplp0203", "uplp0503",
> "uplp0803", "uplp0104", "uplp0704",
"uplp0804", "uplp1204", "uplp0805",
> "uplp1005", "uplp0106", "dnlp1201",
"dnlp0502", "dnlp0702", "dnlp1002",
> "dnlp1102", "dnlp1202", "dnlp0103",
"dnlp0203", "dnlp0303", "dnlp0403",
> "dnlp0503", "dnlp0803", "dnlp0104",
"dnlp0704", "dnpt0804", "dnlp1204",
> "dnlp0805", "dnlp1005", "dnlp0106",
"uprk1201", "uprk0502", "uprk0702",
> "uprk1002", "uprk1102", "uprk0203",
"uprk0503", "uprk0803", "uprk0104",
> "uprk0704", "uprk0804", "uprk1204",
"uprk0805", "uprk1005", "uprk0106",
> "dnrk0502", "dnrk0702", "dnrk1002",
"dnrk1102", "dnrk1202", "dnrk0103",
> "dnrk0203", "dnrk0303", "dnrk0403",
"dnrk0503", "dnrk0803", "dnrk0104",
> "dnrk0704", "dnrk0804", "dnrk1204",
"dnrk0805", "dnrk1005", "dnrk0106",
> "uprt1201", "uprt0502", "uprt0702",
"uprt1002", "uprt1102", "uprt0203",
> "uprt0503", "uprt0803", "uprt0104",
"uprt0704", "uprt0804", "uprt1204",
> "uprt0805", "uprt1005", "uprt0106",
"dnrt1201", "dnrt0502", "dnrt0702",
> "dnrt1002", "dnrt0403", "dnrt0803",
"dnrt0104", "dnpt0704", "dnrt0804",
> "dnrt0805", "dnrt1005", "dnrt0106",
"upsd1201", "upsd0502", "upsd0702",
> "upsd1002", "upsd1102", "upsd0203",
"upsd0503", "upsd0803", "upsd0104",
> "upsd0704", "upsd0804", "upsd1204",
"upsd0805", "upsd1005", "upsd0106",
> "dnsd1201", "dnsd0502", "dnsd0702",
"dnsd1002", "dnsd1102", "dnsd1202",
> "dnsd0103", "dnsd0203", "dnsd0303",
"dnsd0403", "dnsd0503", "dnsd0803",
> "dnsd0104", "dnsd0704", "dnsd0804",
"dnsd1204", "dnsd0805", "dnsd1005",
> "dnsd0106")
>
> these are the rownames of a dataframe, and I would like to split them
> up into chunks of two letters, two letter, and then the four numbers.
> The problem that I am trying to solve is to add the numbers in the
> columns (unique counts of species) that correspond to a "whole
sample"
> :
>
> a whole sample consists of one of "1" all six of "2"
for a particular date "3"
>
> 1
> up= unrestored
> down=restored
>
> 2
> habitat types
> sd
> rk
> rt
> pl
> lp
> wd
>
> 3
> date - self explanitory
>
> strsplit looks promising, but I don't know what a regular expression
> is or how to use it for that matter
> --
> Stephen Sefick
> Research Scientist
> Southeastern Natural Sciences Academy
>
> Let's not spend our time and resources thinking about things that are
> so little or so large that all they really do for us is puff us up and
> make us feel like gods. We are mammals, and have not exhausted the
> annoying little problems of being mammals.
>
>        -K. Mullis
>
> ______________________________________________
> R-help at 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.
>


-- 
Henrique Dallazuanna
Curitiba-Paran?-Brasil
25? 25' 40" S 49? 16' 22" O