curve {graphics}  R Documentation 
Draws a curve corresponding to a function over the interval
[from, to]
. curve
can plot also an expression in the variable
xname
, default ‘x’.
curve(expr, from = NULL, to = NULL, n = 101, add = FALSE,
type = "l", xname = "x", xlab = xname, ylab = NULL,
log = NULL, xlim = NULL, ...)
## S3 method for class 'function'
plot(x, y = 0, to = 1, from = y, xlim = NULL, ylab = NULL, ...)
expr 
The name of a function, or a call or an
expression written as a function of 
x 
a ‘vectorizing’ numeric R function. 
y 
alias for 
from, to 
the range over which the function will be plotted. 
n 
integer; the number of x values at which to evaluate. 
add 
logical; if 
xlim 

type 
plot type: see 
xname 
character string giving the name to be used for the x axis. 
xlab, ylab, log, ... 
labels and graphical parameters
can also be specified as arguments. See ‘Details’ for the
interpretation of the default for For the 
The function or expression expr
(for curve
) or function
x
(for plot
) is evaluated at n
points equally
spaced over the range [from, to]
. The points determined in
this way are then plotted.
If either from
or to
is NULL
, it defaults to the
corresponding element of xlim
if that is not NULL
.
What happens when neither from
/to
nor xlim
specifies both xlimits is a complex story. For
plot(<function>)
and for curve(add = FALSE)
the defaults
are (0, 1)
. For curve(add = NA)
and curve(add =
TRUE)
the defaults are taken from the xlimits used for the previous
plot. (This differs from versions of R prior to 2.14.0.)
The value of log
is used both to specify the plot axes (unless
add = TRUE
) and how ‘equally spaced’ is interpreted: if
the x component indicates logscaling, the points at which the
expression or function is plotted are equally spaced on log scale.
The default value of log
is taken from the current plot when
add = TRUE
, whereas if add = NA
the x component is taken
from the existing plot (if any) and the y component defaults to
linear. For add = FALSE
the default is ""
This used to be a quick hack which now seems to serve a useful purpose, but can give bad results for functions which are not smooth.
For expensivetocompute expr
essions, you should use smarter tools.
The way curve
handles expr
has caused confusion. It
first looks to see if expr
is a name (also known as a
symbol), in which case it is taken to be the name of a function, and
expr
is replaced by a call to expr
with a single
argument with name given by xname
. Otherwise it checks that
expr
is either a call or an expression, and that
it contains a reference to the variable given by xname
(using
all.vars
): anything else is an error. Then expr
is evaluated in an environment which supplies a vector of name given
by xname
of length n
, and should evaluate to an object
of length n
. Note that this means that curve(x, ...)
is
taken as a request to plot a function named x
(and it is used
as such in the function
method for plot
).
The plot
method can be called directly as plot.function
.
A list with components x
and y
of the points that were
drawn is returned invisibly.
For historical reasons, add
is allowed as an argument to the
"function"
method of plot
, but its behaviour may surprise
you. It is recommended to use add
only with curve
.
splinefun
for spline interpolation, lines
.
plot(qnorm) # default range c(0, 1) is appropriate here,
# but end values are /+Inf and so are omitted.
plot(qlogis, main = "The Inverse Logit : qlogis()")
abline(h = 0, v = 0:2/2, lty = 3, col = "gray")
curve(sin, 2*pi, 2*pi, xname = "t")
curve(tan, xname = "t", add = NA,
main = "curve(tan) > same xscale as previous plot")
op < par(mfrow = c(2, 2))
curve(x^3  3*x, 2, 2)
curve(x^2  2, add = TRUE, col = "violet")
## simple and advanced versions, quite similar:
plot(cos, pi, 3*pi)
curve(cos, xlim = c(pi, 3*pi), n = 1001, col = "blue", add = TRUE)
chippy < function(x) sin(cos(x)*exp(x/2))
curve(chippy, 8, 7, n = 2001)
plot (chippy, 8, 5)
for(ll in c("", "x", "y", "xy"))
curve(log(1+x), 1, 100, log = ll, sub = paste0("log = '", ll, "'"))
par(op)