Displaying 3 results from an estimated 3 matches for "r_lowesw".
2006 Jul 02
1
prefix 'R_' when calling external code
I noticed that in
https://svn.r-project.org/R/trunk/src/library/stats/R/loess.R
that we are now calling R_loess_raw, R_lowesw, R_lowesp, etc. I'm
interested to know what is the benefit/reason for the 'R_', as I am
unfamiliar with this prefix and do not see it mentioned in 'Writing R
Extensions.'
Thanks,
Ben
2008 Feb 25
1
r44608 fails make check-all in scatter.smooth example
...())
>
> ### Name: scatter.smooth
> ### Title: Scatter Plot with Smooth Curve Fitted by Loess
> ### Aliases: scatter.smooth loess.smooth
> ### Keywords: smooth
>
> ### ** Examples
>
> require(graphics)
>
> with(cars, scatter.smooth(speed, dist))
Error in .Fortran(R_lowesw, as.double(fitted.residuals), as.integer(N), :
Incorrect number of arguments (4), expecting 7 for lowesw
Calls: with ... scatter.smooth -> loess.smooth -> simpleLoess -> .Fortran
Execution halted
This is on Fedora 8.
Plots on the new X11() device look very nice though!
Cheers,
G
--...
2011 Jun 16
0
Update: Is there an implementation of loess with more than 3 parametric predictors or a trick to a similar effect?
...delta1 = double(1),
delta2 = double(1),
as.integer(surf.stat == "interpolate/exact"))
if(j==1) {
trace.hat.out <- z$trL
one.delta <- z$delta1
two.delta <- z$delta2
}
fitted.residuals <- y - z$fitted.values
if(j < iterations)
robust <- .Fortran(R_lowesw,
as.double(fitted.residuals),
as.integer(N),
robust = double(N),
integer(N))$robust
}
if(surface == "interpolate")
{
pars <- z$parameter
names(pars) <- c("d", "n", "vc", "nc", "nv"...