Since you indicated there are six more columns in the data.frame, getSample
modified below to take care of it.
> getSample
function(x)
{
sites <- unique(x$SiteID)
years <- unique(x$Year)
result <- data.frame()
x$ID <- seq(1,nrow(x))
for (i in 1:length(sites))
{
for (j in 1:length(years))
{
if (nrow(x[as.character(x$SiteID)==as.character(sites[i]) &
x$Year==years[j],]) > 3)
{
sampledID <- sample(x[as.character(x$SiteID)==as.character(sites[i])
& x$Year==years[j],]$ID,3,replace=FALSE)
for (k in 1:length(sampledID))
{
result <- rbind(result,x[x$ID==sampledID[k],-ncol(x)])
}
}
}
}
names(result) <- names(x)[-ncol(x)]
rownames(result) <- NULL
return(result)
}
> getSample(fitting.set)
IDbyYear SiteID Year
1 42.24 A-Airport 2006
2 42.24 A-Airport 2006
3 42.24 A-Airport 2006
--
View this message in context:
http://r.789695.n4.nabble.com/sampling-dataframe-based-upon-number-of-record-occurrences-tp4704144p4704155.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
[email protected] mailing list -- To UNSUBSCRIBE and more, see
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.
