ggplot box plot confusion [duplicate] - r

Question

I'm trying to use ggplot2 / geom_boxplot to produce a boxplot where the whiskers are defined as the 5 and 95th percentile instead of 0.25 - 1.5 IQR / 0.75 + IQR and outliers from those new whiskers are plotted as usual. I can see that the geom_boxplot aesthetics include ymax / ymin, but it's not clear to me how I put values in here. It seems like:
stat_quantile(quantiles = c(0.05, 0.25, 0.5, 0.75, 0.95))
should be able to help, but I don't know how to relate the results of this stat to set the appropriate geom_boxplot() aesthetics:
geom_boxplot(aes(ymin, lower, middle, upper, ymax))
I've seen other posts where people mention essentially building a boxplot-like object manually, but I'd rather keep the whole boxplot gestalt intact, just revising the meaning of two of the variables being drawn.

Answer 1

geom_boxplot with stat_summary can do it:
# define the summary function
f <- function(x) {
r <- quantile(x, probs = c(0.05, 0.25, 0.5, 0.75, 0.95))
names(r) <- c("ymin", "lower", "middle", "upper", "ymax")
r
}
# sample data
d <- data.frame(x=gl(2,50), y=rnorm(100))
# do it
ggplot(d, aes(x, y)) + stat_summary(fun.data = f, geom="boxplot")
# example with outliers
# define outlier as you want
o <- function(x) {
subset(x, x < quantile(x)[2] | quantile(x)[4] < x)
}
# do it
ggplot(d, aes(x, y)) +
stat_summary(fun.data=f, geom="boxplot") +
stat_summary(fun.y = o, geom="point")

Answer 2

It is now possible to specify the whiskers endpoints in ggplot2_2.1.0. Copying from the examples in ?geom_boxplot:
# It's possible to draw a boxplot with your own computations if you
# use stat = "identity":
y <- rnorm(100)
df <- data.frame(
x = 1,
y0 = min(y),
y25 = quantile(y, 0.25),
y50 = median(y),
y75 = quantile(y, 0.75),
y100 = max(y)
)
ggplot(df, aes(x)) +
geom_boxplot(
aes(ymin = y0, lower = y25, middle = y50, upper = y75, ymax = y100),
stat = "identity"
)

Answer 3

Building on #konvas's answer, beginning in ggplot2.0.x, you can extend ggplot using the ggproto system and define your own stat.
By copying the ggplot2 stat_boxplot code and making a few edits, you can quickly define a new stat (stat_boxplot_custom) that takes the percentiles you want to use as an argument (qs) instead of the coef argument that stat_boxplot uses. The new stat is defined here:
# modified from https://github.com/tidyverse/ggplot2/blob/master/R/stat-boxplot.r
library(ggplot2)
stat_boxplot_custom <- function(mapping = NULL, data = NULL,
geom = "boxplot", position = "dodge",
...,
qs = c(.05, .25, 0.5, 0.75, 0.95),
na.rm = FALSE,
show.legend = NA,
inherit.aes = TRUE) {
layer(
data = data,
mapping = mapping,
stat = StatBoxplotCustom,
geom = geom,
position = position,
show.legend = show.legend,
inherit.aes = inherit.aes,
params = list(
na.rm = na.rm,
qs = qs,
...
)
)
}
Then, the layer function is defined. Note that b/c I copied directly from stat_boxplot, you have to access a few internal ggplot2 functions using :::. This includes a lot of stuff copied directly over from StatBoxplot, but the key area is in computing the stats directly from the qs argument: stats <- as.numeric(stats::quantile(data$y, qs)) inside of the compute_group function.
StatBoxplotCustom <- ggproto("StatBoxplotCustom", Stat,
required_aes = c("x", "y"),
non_missing_aes = "weight",
setup_params = function(data, params) {
params$width <- ggplot2:::"%||%"(
params$width, (resolution(data$x) * 0.75)
)
if (is.double(data$x) && !ggplot2:::has_groups(data) && any(data$x != data$x[1L])) {
warning(
"Continuous x aesthetic -- did you forget aes(group=...)?",
call. = FALSE
)
}
params
},
compute_group = function(data, scales, width = NULL, na.rm = FALSE, qs = c(.05, .25, 0.5, 0.75, 0.95)) {
if (!is.null(data$weight)) {
mod <- quantreg::rq(y ~ 1, weights = weight, data = data, tau = qs)
stats <- as.numeric(stats::coef(mod))
} else {
stats <- as.numeric(stats::quantile(data$y, qs))
}
names(stats) <- c("ymin", "lower", "middle", "upper", "ymax")
iqr <- diff(stats[c(2, 4)])
outliers <- (data$y < stats[1]) | (data$y > stats[5])
if (length(unique(data$x)) > 1)
width <- diff(range(data$x)) * 0.9
df <- as.data.frame(as.list(stats))
df$outliers <- list(data$y[outliers])
if (is.null(data$weight)) {
n <- sum(!is.na(data$y))
} else {
# Sum up weights for non-NA positions of y and weight
n <- sum(data$weight[!is.na(data$y) & !is.na(data$weight)])
}
df$notchupper <- df$middle + 1.58 * iqr / sqrt(n)
df$notchlower <- df$middle - 1.58 * iqr / sqrt(n)
df$x <- if (is.factor(data$x)) data$x[1] else mean(range(data$x))
df$width <- width
df$relvarwidth <- sqrt(n)
df
}
)
There is also a gist here, containing this code.
Then, stat_boxplot_custom can be called just like stat_boxplot:
library(ggplot2)
y <- rnorm(100)
df <- data.frame(x = 1, y = y)
# whiskers extend to 5/95th percentiles by default
ggplot(df, aes(x = x, y = y)) +
stat_boxplot_custom()
# or extend the whiskers to min/max
ggplot(df, aes(x = x, y = y)) +
stat_boxplot_custom(qs = c(0, 0.25, 0.5, 0.75, 1))