sinaplot (version 1.1.0)

sinaplot: sinaplot

Description

The SinaPlot is a data visualization chart suitable for plotting any single variable in a multiclass dataset. It is an enhanced jitter strip chart, where the width of the jitter is controlled by the density distribution of the data within each class.

Usage

sinaplot(x, ...)
# S3 method for default
sinaplot(x, groups = NULL, method = c("density",
  "counts"), scale = TRUE, adjust = 0.75, bins = 50, bin_limit = 1,
  maxwidth = 1, seed = NULL, plot = TRUE, add = FALSE, log = FALSE,
  labels = NULL, xlab = "", ylab = "", col = NULL, pch = NULL, ...)
# S3 method for formula
sinaplot(formula, data = NULL, ..., subset,
  na.action = NULL, xlab, ylab)

Arguments

x

numeric vector or a data frame or a list of numeric vectors to be plotted.

...

arguments to be passed to plot.

groups

optional vector of length(x).

method

choose the method to spread the samples within the same bin along the x-axis. Available methods: "density" and "counts". See Details.

scale

a logical that indicates whether the width of each group should be scaled relative to the group with the highest density. Default: TRUE.

adjust

adjusts the bandwidth of the density kernel when method == "density" (see density).

bins

number of bins to divide the y-axis into when method == "counts". Default: 50.

bin_limit

if the samples within the same y-axis bin are more than bin_limit, the samples's X coordinates will be adjusted.

maxwidth

control the maximum width the points can spread into. Values between 0 and 1.

seed

a single value that controls the random sample jittering. Set to an integer to enable plot reproducibility. Default NULL.

plot

logical. When TRUE the sinaplot is produced, otherwise the function returns the new sample coordinates. Default: TRUE.

add

logical. If true add boxplot to current plot.

log

logical. If true it uses a logarihmic scale on the y-axis.

labels

labels for each group. Recycled if necessary. By default, these are inferred from the data.

xlab, ylab

axis labels.

pch, col

plotting characters and colors, specified by group. Recycled if necessary.

formula

a formula, such as y ~ grp, where y is a numeric vector of data values to be split into groups according to the grouping variable grp (usually a factor).

data

a data.frame (or list) from which the variables in formula should be taken.

subset

an optional vector specifying a subset of observations to be used for plotting.

na.action

a function which indicates what should happen when the data contain NAs. The default is to ignore missing values in either the response or the group.

Value

x

discrete x-coordinates, split by group

y

input values

group

input groups

scaled

final x-coordinates, adjusted by sinaplot

NULL NULL

Details

There are two available ways to define the x-axis borders for the samples to spread within:

• method = "density" A density kernel is estimated along the y-axis for every sample group. The borders are then defined by the density curve. Tuning parameter adjust can be used to control the density bandwidth in the same way it is used in density.
• method = "counts": The borders are defined by the number of samples that occupy the same bin and the parameter maxwidth in the following fashion: xBorder = nsamples * maxwidth

Examples

## sinaplot on a formula:

data("blood", package = "sinaplot")
boxplot(Gene ~ Class, data = blood)
sinaplot(Gene ~ Class, data = blood, pch = 20, add = TRUE)

## sinaplot on a data.frame:

df <- data.frame(Uni05 = (1:100)/21, Norm = rnorm(100),
                  `5T` = rt(100, df = 5), Gam2 = rgamma(100, shape = 2))
boxplot(df)
sinaplot(df, add = TRUE, pch = 20)

## sinaplot on a list:

bimodal <- c(rnorm(300, -2, 0.6), rnorm(300, 2, 0.6))
uniform <- runif(500, -4, 4)
normal <- rnorm(800,0,3)

distributions <- list(uniform = uniform, bimodal = bimodal, normal = normal)
boxplot(distributions, col = 2:4)
sinaplot(distributions, add = TRUE, pch = 20)

## sinaplot on a vector:

x <- c(rnorm(200, 4, 1), rnorm(200, 5, 2), rnorm(400, 6, 1.5))
groups <- c(rep("Cond1", 200), rep("Cond2", 200), rep("Cond3", 400))

sinaplot(x, groups)

par(mfrow = c(2, 2))

sinaplot(x, groups, pch = 20, col = 2:4)
sinaplot(x, groups, scale = FALSE, pch = 20, col = 2:4)
sinaplot(x, groups, scale = FALSE, adjust = 1/6, pch = 20, col = 2:4)
sinaplot(x, groups, scale = FALSE, adjust = 3, pch = 20, col = 2:4)

#blood

par(mfrow = c(1,1))
sinaplot(blood$Gene, blood$Class)

old.mar <- par()$mar
par(mar = c(9,4,4,2) + 0.1)
groups <- levels(blood$Class)

sinaplot(blood$Gene, blood$Class, pch = 20, xaxt = "n", col = rainbow(18))
axis(1, at = 1:length(groups), labels = FALSE)
text(1:length(groups), y = par()$usr[3] - 0.1 * (par()$usr[4] - par()$usr[3]),
     xpd = TRUE, srt = 45, adj = 1, labels = groups)
par(mar = old.mar)