cut membagi rentang x menjadi beberapa interval dan mengkodekan nilai dalam x sesuai dengan intervalnya. Interval paling kiri berhubungan dengan level satu, interval paling kiri berikutnya berhubungan dengan level dua, dan seterusnya.
cut(x, …)<p></p><p># S3 method for default
cut(x, breaks, labels = NULL,
include.lowest = FALSE, right = TRUE, dig.lab = 3,
ordered_result = FALSE, …)</p>| Parameter | Deskripsi |
|---|---|
x |
a numeric vector which is to be converted to a factor by cutting. |
breaks |
either a numeric vector of two or more unique cut points or a single number (greater than or equal to 2) giving the number of intervals into which x is to be cut. |
labels |
labels for the levels of the resulting category. By default, labels are constructed using "(a,b]" interval notation. If labels = FALSE, simple integer codes are returned instead of a factor. |
include.lowest |
logical, indicating if an ‘x[i]’ equal to the lowest (or highest, for right = FALSE) ‘breaks’ value should be included. |
right |
logical, indicating if the intervals should be closed on the right (and open on the left) or vice versa. |
dig.lab |
integer which is used when labels are not given. It determines the number of digits used in formatting the break numbers. |
ordered_result |
logical: should the result be an ordered factor? |
… |
further arguments passed to or from other methods. |
# NOT RUN {
Z <- stats::rnorm(10000)
table(cut(Z, breaks = -6:6))
sum(table(cut(Z, breaks = -6:6, labels = FALSE)))
sum(graphics::hist(Z, breaks = -6:6, plot = FALSE)$counts)
cut(rep(1,5), 4) #-- dummy
tx0 <- c(9, 4, 6, 5, 3, 10, 5, 3, 5)
x <- rep(0:8, tx0)
stopifnot(table(x) == tx0)
table( cut(x, b = 8))
table( cut(x, breaks = 3*(-2:5)))
table( cut(x, breaks = 3*(-2:5), right = FALSE))
##--- some values OUTSIDE the breaks :
table(cx <- cut(x, breaks = 2*(0:4)))
table(cxl <- cut(x, breaks = 2*(0:4), right = FALSE))
which(is.na(cx)); x[is.na(cx)] #-- the first 9 values 0
which(is.na(cxl)); x[is.na(cxl)] #-- the last 5 values 8
## Label construction:
y <- stats::rnorm(100)
table(cut(y, breaks = pi/3*(-3:3)))
table(cut(y, breaks = pi/3*(-3:3), dig.lab = 4))
table(cut(y, breaks = 1*(-3:3), dig.lab = 4))
# extra digits don't "harm" here
table(cut(y, breaks = 1*(-3:3), right = FALSE))
#- the same, since no exact INT!
## sometimes the default dig.lab is not enough to be avoid confusion:
aaa <- c(1,2,3,4,5,2,3,4,5,6,7)
cut(aaa, 3)
cut(aaa, 3, dig.lab = 4, ordered = TRUE)
## one way to extract the breakpoints
labs <- levels(cut(aaa, 3))
cbind(lower = as.numeric( sub("\\((.+),.*", "\\1", labs) ),
upper = as.numeric( sub("[^,]*,([^]]*)\\]", "\\1", labs) ))
# }