dendextend (version 1.1.2)

colored_bars: Add colored bars to a dendrogram

Description

Add colored bars to a dendrogram, usually corresponding to either clusters or some outside categorization.

Usage

colored_bars(colors, dend, rowLabels = NULL, cex.rowLabels = 0.9,
  add = TRUE, y_scale, y_shift, text_shift = 1,
  sort_by_labels_order = FALSE, ...)

Arguments

colors

Coloring of objects on the dendrogram. Either a vector (one color per object) or a matrix (can also be an array or a data frame) with each column giving one color per object. Each column will be plotted as a horizontal row of colors under the dendrogr

dend

a dendrogram object. If missing, the colors are plotted without and re-ordering (this assumes that the colors are already ordered based on the dend's labels) This is also important in order to get the correct height/location of the colored bars (i.e.:

rowLabels

Labels for the colorings given in colors. The labels will be printed to the left of the color rows in the plot. If the argument is given, it must be a vector of length equal to the number of columns in colors. If not given,

cex.rowLabels

Font size scale factor for the row labels. See par.

add

logical(TRUE), should the colored bars be added to an existing dendrogram plot?

y_scale

how much should the bars be stretched on the y axis? If no dend is supplied - the default will be 1

y_shift

where should the bars be plotted underneath the x axis? By default it will try to locate the bars underneath the labels (it may miss, in which case you would need to enter a number manually) If no dend is supplied - the default will be 0

text_shift

a dendrogram object

sort_by_labels_order

logical(FALSE) - if TRUE, then the order of the colored bars will be sorted based on the order needed to change the original order of the observations to the current order of the labels in the dendrogram. If FALSE (default) the colored bars are plotted

...

ignored at this point.

Value

• An invisible vector/matrix with the ordered colors.

source

This function is based on the plotHclustColors from the {moduleColor} R package. It was modified so that it would work with dendrograms (and not just hclust objects), as well allow to add the colored bars on top of an existing plot (and not only as a seperate plot). See: http://cran.r-project.org/package=moduleColor For more details.

Details

You will often needs to adjust the y_scale, y_shift and the text_shift parameters, in order to get the bars in the location you would want. (this can probably be done automatically, but will require more work. since it has to do with the current mar settings, the number of groups, and each computer's specific graphic device. patches for smarter defaults will be appreciated)

See Also

branches_attr_by_clusters, plotDendroAndColors

Examples

rows_picking <- c(1:5, 25:30)
dend <- (iris[rows_picking,-5]*10) %>% dist %>% hclust %>% as.dendrogram
odd_numbers <- rows_picking %% 2
cols <- c("gold", "grey")[odd_numbers+1]
# scale is off
plot(dend)
colored_bars(dend, cols)
# move and scale a bit
plot(dend)
colored_bars(dend, cols, y_shift = -1,
             rowLabels = "Odd\n numbers")
# Now let's cut the tree and add that info to the plot:
k2 <- cutree(dend, k = 2)
cols2 <- c("#0082CE", "#CC476B")[k2]
plot(dend)
# sadly, the shift paramteres need to be handled manually...
colored_bars(dend, cbind(cols2, cols), y_shift = -1,
             rowLabels = c("2 clusters", "Odd numbers"),
             text_shift = 1)

# let's add clusters color
# notice how we need to play with the colors a bit
# this is because color_branches places colors from
# left to right. Which means we need to give colored_bars
# the colors of the items so that ofter sorting they would be
# from left to right. Here is how it can be done:
the_k <- 3
library(colorspace)
cols3 <- rainbow_hcl(the_k, c=90, l=50)
dend %>% update("branches_k_color", k = the_k, with = cols3) %>% plot

kx <- cutree(dend, k = the_k)
ord <- order.dendrogram(dend)
kx  <- sort_levels_values(kx[ord])
kx  <- kx[match(seq_along(ord), ord)]

colored_bars(dend, cbind(cols3[kx], cols2, cols),
             y_shift = -1, y_scale = 1.4,
             rowLabels = c("3 clusters", "2 clusters", "Odd numbers"),
             text_shift = 1)