picketplot {Heatplus}R Documentation

Barplots for Several Binary Variables

Description

Display one or more binary variables by using black bars for presence/validity of a condition, empty space for absence/invalidity, and an extra color for missing values. Additionally, an index plot for one interval scaled variable can be added, possibly with a smoothing function.

This routine is primarily intended for augmenting heatmaps. It might be useful in other contexts, but misses most frills for using it comfortably.

Usage

picketplot(x, covariate = NULL, grp = NULL, grpcol, grplabel = NULL, 
           add = FALSE, control = list())

Arguments

x a matrix or data frame containing the data.
covariate the index of the column in x that contains the interval scaled variable, if any.
grp cluster indices for the rows of x, used for assigning background color.
grpcol colors corresponding to the clusters.
grplabel cluster names.
add logical indicating whether to start a new plot, or whether to add the plot to the existing one.
control a list of parameters controlling the appearance of the plot, see Details.

Details

The following named list elements can be set to change the appearance of the plot:

boxw
the relative width of a marking box.
boxh
the relative height of a marking box.
hbuff
the horizontal separation around marking boxes; equals half the horizontal distance between two marking boxes.
vbuff
ditto for vertical separation.
span
passed on to loess used for the smoothing curve.
nacol
color for missing values of binary variables.
degree
if 0, no smoothing line is drawn; otherwise passed on to loess used for the smoothing curve.
cex.label
the character size for grplabel.

Note

The plot looks like a more or less derelict picket fence, and 'picketplot' sounds somewhat like the 'pocketplot' used in geostatistics.

Author(s)

Alexander Ploner <Alexander.Ploner@ki.se>

See Also

heatmap_plus

Examples

# without covariate
mm = cbind(sample(0:1, 42, rep=TRUE), sample(0:1, 42, rep=TRUE))
mm[sample(42, 5), 1] = NA
picketplot(mm)

# with clustering
cl = rep(1:3, c(10,22,10))
cn = c("Cluster I","Cluster II","Cluster III")
cc = c("lightblue","lightgreen","lightpink") # windows palette
picketplot(mm, grp=cl, grplabel=cn, grpcol=cc)

# add a covariate; setting the colnames makes the variable labels
mm = cbind(mm, rnorm(42) + cl/2)
colnames(mm) = c("State A","State B", "X")
picketplot(mm, covariate=3,grp=cl, grplabel=cn, grpcol=cc)

# using extra controls
picketplot(mm, covariate=3,grp=cl, grplabel=cn, grpcol=cc, control=list(nacol="white", degree=0))


[Package Heatplus version 1.6.0 Index]