Data labels for mean and percentiles in a distribution chart - r

Question

I'm creating a custom chart to visualize a variable's distribution using geom_density. I added 3 vertical lines for a custom value, the 5th percentile and the 95th percentile.
How do I add labels for those lines?
I tried using geom_text but i don't know how to parameter the x and y variables
library(ggplot2)
ggplot(dataset, aes(x = dataset$`Estimated percent body fat`)) +
geom_density() +
geom_vline(aes(xintercept = dataset$`Estimated percent body fat`[12]),
color = "red", size = 1) +
geom_vline(aes(xintercept = quantile(dataset$`Estimated percent body fat`,
0.05, na.rm = TRUE)),
color = "grey", size = 0.5) +
geom_vline(aes(xintercept = quantile(dataset$`Estimated percent body fat`,
0.95, na.rm = TRUE)),
color="grey", size=0.5) +
geom_text(aes(x = dataset$`Estimated percent body fat`[12],
label = "Custom", y = 0),
colour = "red", angle = 0)
I'd like to obtain the following:
for the custom value, I'd like to add the label at the top of the chart, just to the right of the line
for the percentiles label, I'd like to add them in the middle of the chart; at the left of the line for the 5th percentile and right of the line for 95th percentile
Here is what I was able to obtain https://i.imgur.com/thSQwyg.png
And these are the first 50 lines of my dataset:
structure(list(`Respondent sequence number` = c(21029L, 21034L,
21043L, 21056L, 21067L, 21085L, 21087L, 21105L, 21107L, 21109L,
21110L, 21125L, 21129L, 21138L, 21141L, 21154L, 21193L, 21195L,
21206L, 21215L, 21219L, 21221L, 21232L, 21239L, 21242L, 21247L,
21256L, 21258L, 21287L, 21310L, 21325L, 21367L, 21380L, 21385L,
21413L, 21418L, 21420L, 21423L, 21427L, 21432L, 21437L, 21441L,
21444L, 21453L, 21466L, 21467L, 21477L, 21491L, 21494L, 21495L
), `Estimated percent body fat` = c(NA, 7.2, NA, NA, 24.1, 25.1,
30.2, 23.6, 24.3, 31.4, NA, 14.1, 20.5, NA, 23.1, 30.6, 21, 20.9,
NA, 24, 26.7, 16.6, NA, 26.9, 16.9, 21.3, 15.9, 27.4, 13.9, NA,
20, NA, 12.8, NA, 33.8, 18.1, NA, NA, 28.4, 10.9, 38.1, 33, 39.3,
15.9, 32.7, NA, 20.4, 16.8, NA, 29)), row.names = c(NA, 50L), class =
"data.frame")

Answer 1

First I recommend clean column names.
dat <- dataset
names(dat) <- tolower(gsub("\\s", "\\.", names(dat)))
Whith base R plots you could do the following. The clou is, that you can store the quantiles and custom positions to use them as coordinates later which gives you a dynamic positioning. I'm not sure if/how this is possible with ggplot.
plot(density(dat$estimated.percent.body.fat, na.rm=TRUE), ylim=c(0, .05),
main="Density curve")
abline(v=c1 <- dat$estimated.percent.body.fat[12], col="red")
abline(v=q1 <- quantile(dat$estimated.percent.body.fat, .05, na.rm=TRUE), col="grey")
abline(v=q2 <- quantile(dat$estimated.percent.body.fat, .95, na.rm=TRUE), col="grey")
text(c1 + 4, .05, c(expression("" %<-% "custom")), cex=.8)
text(q1 - 5.5, .025, c(expression("5% percentile" %->% "")), cex=.8)
text(q2 + 5.5, .025, c(expression("" %<-% "95% percentile")), cex=.8)
Note: Case you don't like the arrows just do e.g. "5% percentile" instead of c(expression("5% percentile" %->% "")).
Or in ggplot you could use annotate.
library(ggplot2)
ggplot(dataset, aes(x = dataset$`Estimated percent body fat`)) +
geom_density() +
geom_vline(aes(xintercept = dataset$`Estimated percent body fat`[12]),
color = "red", size = 1) +
geom_vline(aes(xintercept = quantile(dataset$`Estimated percent body fat`,
0.05, na.rm = TRUE)),
color = "grey", size = 0.5) +
geom_vline(aes(xintercept = quantile(dataset$`Estimated percent body fat`,
0.95, na.rm = TRUE)),
color="grey", size=0.5) +
annotate("text", x=16, y=.05, label="custom") +
annotate("text", x=9.5, y=.025, label="5% percentile") +
annotate("text", x=38, y=.025, label="95% percentile")
Note, that in either solution the result (i.e. exact label positions) depends on your export size. To learn how to control this, take e.g. a look into How to save a plot as image on the disk?.
Data
dataset <- structure(list(`Respondent sequence number` = c(21029L, 21034L,
21043L, 21056L, 21067L, 21085L, 21087L, 21105L, 21107L, 21109L,
21110L, 21125L, 21129L, 21138L, 21141L, 21154L, 21193L, 21195L,
21206L, 21215L, 21219L, 21221L, 21232L, 21239L, 21242L, 21247L,
21256L, 21258L, 21287L, 21310L, 21325L, 21367L, 21380L, 21385L,
21413L, 21418L, 21420L, 21423L, 21427L, 21432L, 21437L, 21441L,
21444L, 21453L, 21466L, 21467L, 21477L, 21491L, 21494L, 21495L
), `Estimated percent body fat` = c(NA, 7.2, NA, NA, 24.1, 25.1,
30.2, 23.6, 24.3, 31.4, NA, 14.1, 20.5, NA, 23.1, 30.6, 21, 20.9,
NA, 24, 26.7, 16.6, NA, 26.9, 16.9, 21.3, 15.9, 27.4, 13.9, NA,
20, NA, 12.8, NA, 33.8, 18.1, NA, NA, 28.4, 10.9, 38.1, 33, 39.3,
15.9, 32.7, NA, 20.4, 16.8, NA, 29)), row.names = c(NA, 50L), class =
"data.frame")