[R] lattice problem in R-1.9.0

[Deepayan Sarkar]

On Tuesday 13 April 2004 12:51, Sundar Dorai-Raj wrote:
> Hi all,
>    I just installed R-1.9.0 on Windows 2000 from binaries. Yesterday,
> on R-1.8.1 I ran a script that looked like:
>
> library(lattice)
> tmp <- expand.grid(A = 1:3, B = letters[1:2])
> tmp$z <- runif(NROW(tmp))
> trellis.device(png, file = "x1081.png", theme = col.whitebg)
> xyplot(z ~ A | B, data = tmp,
>         panel = function(x, y, i) {
>           panel.xyplot(x, y)
>           ltext(1, 0.95, paste("i =", i), adj = 0)
>         },
>         ylim = c(0, 1),
>         i = 10)
> dev.off()
>
> In R-1.9.0, the same script gives the following error message:
>
> Error in trellis.skeleton(cond = structure(list(B =
> structure(as.integer(c(1,  :
> 	Invalid value of index.cond
                         ^^^^^^^^^^


> I've tracked it down to including the argument "i" to the panel
> function. If I change the argument to
>
> xyplot(z ~ A | B, data = tmp,
>         panel = function(x, y, I) {
>           panel.xyplot(x, y)
>           ltext(1, 0.95, paste("i =", I), adj = 0)
>         },
>         ylim = c(0, 1),
>         I = 10)
>
> all is copacetic. There is no argument in xyplot that starts with "i"
> so I don't know where the partial matching is occurring.

Actually, in R 1.9.0, xyplot() does have a new argument that starts with 
i, namely 'index.cond' (as indicated by the error message above). This 
(along with many other arguments) doesn't show up in args(xyplot) 
because of the way arguments common to high-level lattice functions are 
handled by common code (they are formally part of ...); but it is 
documented in ?xyplot.

Deepayan