Understanding how `levelplot` is done in R

Question

On the example given below, which can easily be done using the levelplot function of R , I would like to ask a question of interpretation: if, for example, I have several values with drat on the x axis, and hp on the y-axis, how R decided which color to put in the cell referring to the cross-section of drat with hp ? Is it by the mean of these various values? Or is it if most of them are in the defined range?

Anyway ... I researched this and found nothing that could answer my question. If anyone can help, thank you in advance.

Answer 1

Have a look at the 'panel' argument, which inherets from 'xyplot', and argument 'panel' inherits from 'scales'. Consider specifying these. Or consider specifying the 'at' argument in levelplot().

level.colors(panel='xyplot(at=)

where at = breakpoints along the range (-1 to +1)

R levelplot adjust axes

https://stat.ethz.ch/R-manual/R-devel/library/lattice/html/levelplot.html

https://stat.ethz.ch/pipermail/r-help/2010-January/223707.html

Answer 2

Numerical values ranging 1 to -1 and all on-diagonal (the lower left to upper right diagonal) values at 1 suggests a correlation matrix is being used as data. Regular users of R will recognize those column names as coming from a subset of the example dataset mtcars 's columns. So any variable has correlation of 1 with itself. I'll demonstrate below.

 cor(mtcars[c('cyl','disp','hp','drat','wt','qsec','vs')])
            cyl       disp         hp        drat         wt        qsec         vs
cyl   1.0000000  0.9020329  0.8324475 -0.69993811  0.7824958 -0.59124207 -0.8108118
disp  0.9020329  1.0000000  0.7909486 -0.71021393  0.8879799 -0.43369788 -0.7104159
hp    0.8324475  0.7909486  1.0000000 -0.44875912  0.6587479 -0.70822339 -0.7230967
drat -0.6999381 -0.7102139 -0.4487591  1.00000000 -0.7124406  0.09120476  0.4402785
wt    0.7824958  0.8879799  0.6587479 -0.71244065  1.0000000 -0.17471588 -0.5549157
qsec -0.5912421 -0.4336979 -0.7082234  0.09120476 -0.1747159  1.00000000  0.7445354
vs   -0.8108118 -0.7104159 -0.7230967  0.44027846 -0.5549157  0.74453544  1.0000000

levelplot(cor(mtcars[c('cyl','disp','hp','drat','wt','qsec','vs')]))

So the colors represent single values coming from that correlation matrix. each entry is the result of an operation like:

 cor(mtcars$disp, mtcars$cyl)

(I'm not sure why your color scale is so short.)