R help - Oct 2008 - nls, lattice, and conversion over to ggplot

I am trying to figure out how to use ggplot2.  I would like to do the below
with ggplot, but I can not figure out how.  The data provided is a subset of
a much larger data set, but these data are the data necessary to make the
plot.  I think I would rather have the colors become symbols, and I do know
how to do that in lattice, but here is a quick and dirty version.
thanks

r <-(structure(list(TSS = c(2.8, 8.4, 11, 1.3, 4.2, 2, 3.4, 14, 8.2,
3.1, 1.4, 0.9, 0.5, 6.1, 9.2, 0.6, 1, 11, 2.4, 1.2, 1.3, 1.3,
0, 1.8, 8, 11, 11, 8.5, 8.5, 1.8, 13, 4.4, 1.4, 2.1, 0.5, 25,
25, 9.3, 6.1, 1.6, 1.5, 19, 19, 24, 9.6, 1.8, 1.4, 1), GPP = c(1.213695235,
3.817313822, 1.267930498, 10.45692825, 3.268295623, 3.505286001,
4.468225245, 0.915653726, 1.635617261, 3.726133898, 1.363453706,
13.99650967, 1.581182762, 0.417618143, 0.741080504, 1.366790205,
0.969326797, 0.412440872, 1.780215366, 3.515743675, 8.248491445,
0.125726306, 13.95880794, 4.850627229, -0.438311644, 1.537773727,
1.537773727, 3.249103284, 3.249103284, 2.470317011, 0.768531626,
2.633107621, 3.113199095, 0.773824094, 3.208461305, 0.680150068,
0.680150068, 0.026385752, 0.369310858, 8.049276658, 7.487378383,
0.950072035, 0.950072035, 0.763580377, 0.333244629, 5.475999014,
9.235631398, 2.587682905), RiverMile = c(148L, 179L, 185L, 202L,
179L, 185L, 190L, 119L, 148L, 179L, 185L, 202L, 215L, 119L, 202L,
198L, 215L, 148L, 198L, 190L, 202L, 215L, 198L, 198L, 215L, 148L,
148L, 202L, 202L, 215L, 119L, 179L, 185L, 190L, 198L, 61L, 61L,
119L, 148L, 202L, 202L, 61L, 61L, 119L, 148L, 185L, 202L, 215L
)), .Names = c("TSS", "GPP", "RiverMile"), class =
"data.frame", row.names c(12L,
13L, 14L, 19L, 25L, 26L, 28L, 34L, 35L, 36L, 37L, 42L, 44L, 58L,
75L, 85L, 88L, 91L, 97L, 107L, 142L, 144L, 155L, 166L, 169L,
185L, 186L, 201L, 202L, 207L, 219L, 221L, 222L, 224L, 226L, 230L,
231L, 250L, 251L, 258L, 283L, 287L, 288L, 303L, 304L, 306L, 311L,
313L)))

library(lattice)
z <- nls(GPP~(a/(TSS+b)), start=c(a=0.01, b=0.01), data=r)
f <- seq(-1, 29, length=100)
y <- coef(z)["a"]/(f+coef(z)["b"])
xyplot(GPP~TSS, data=r, xlim=c(-0.5, 29), groups=RiverMile ,auto.key=TRUE ,
pch=20 ,panel=function(...)
 {panel.xyplot(...)
 llines(f, y)
}
)


-- 
Stephen Sefick
Research Scientist
Southeastern Natural Sciences Academy

Let's not spend our time and resources thinking about things that are so
little or so large that all they really do for us is puff us up and make us
feel like gods.  We are mammals, and have not exhausted the annoying little
problems of being mammals.

-K. Mullis

	[[alternative HTML version deleted]]

On Thu, Oct 9, 2008 at 2:29 PM, stephen sefick <ssefick at gmail.com>
wrote:
> I am trying to figure out how to use ggplot2.  I would like to do the below
> with ggplot, but I can not figure out how.  The data provided is a subset
of
> a much larger data set, but these data are the data necessary to make the
> plot.  I think I would rather have the colors become symbols, and I do know
> how to do that in lattice, but here is a quick and dirty version.
> thanks
Here's one way:

pred <- data.frame(GPP = f, TSS = y)
qplot(TSS, GPP, data=r, colour=RiverMile) +
geom_line(data=pred, colour ="black")

 * ggplot2 works with data frames, so the key is to create one from
your model predictions.  Naming the variables to match the names of
the model inputs makes sense, and saves some typing.

 *  You no longer need to specify xlim because ggplot2 knows about
everything you are plotting and can calculate the limits
appropriately.

 * You have have to manually set the colour in geom_line to override
the default mapping that you created between colour and RiverMile.

Hadley

-- 
http://had.co.nz/