Related
I have a graph of vertices and edges which I'd like to plot using a fruchtermanreingold layout.
Here's the graph edges matrix:
edge.mat <- matrix(as.numeric(strsplit("3651,0,0,1,0,0,0,0,2,0,11,2,0,0,0,300,0,1,0,0,66,0,78,9,0,0,0,0,0,0,11690,0,1,0,0,0,0,0,0,0,0,493,1,1,0,4288,5,0,0,36,0,9,7,3,0,6,1,0,1,7,490,0,0,0,6,0,0,628,6,12,0,0,0,0,0,641,0,0,4,0,0,0,0,0,0,66,0,0,0,0,3165,0,281,0,0,0,0,0,0,0,0,45,1,0,0,35248,0,1698,2,0,1,0,2,99,0,0,6,29,286,0,31987,0,1,10,0,8,0,16,0,21,1,0,0,1718,0,51234,0,0,17,3,12,0,0,7,0,0,0,1,0,2,16736,0,0,0,3,0,0,4,630,0,0,0,9,0,0,29495,53,6,0,0,0,0,5,0,0,0,0,3,0,19,186,0,0,0,482,8,12,0,1,0,7,1,0,6,0,26338",
split = ",")[[1]]),
nrow = 14,
dimnames = list(LETTERS[1:14], LETTERS[1:14]))
I then create an igraph object from that using:
gr <- igraph::graph_from_adjacency_matrix(edge.mat, mode="undirected", weighted=T, diag=F)
And then use ggnetwork to convert gr to a data.frame, with specified vertex colors:
set.seed(1)
gr.df <- ggnetwork::ggnetwork(gr,
layout="fruchtermanreingold",
weights="weight",
niter=50000,
arrow.gap=0)
And then I plot it using ggplot2 and ggnetwork:
vertex.colors <- strsplit("#00BE6B,#DC2D00,#F57962,#EE8044,#A6A400,#62B200,#FF6C91,#F77769,#EA8332,#DA8E00,#C59900,#00ACFC,#C49A00,#DC8D00",
split=",")[[1]]
library(ggplot2)
library(ggnetwork)
ggplot(gr.df, aes(x = x, y = y, xend = xend, yend = yend)) +
geom_edges(color = "gray", aes(size = weight)) +
geom_nodes(color = "black")+
geom_nodelabel(aes(label = vertex.names),
color = vertex.colors, fontface = "bold")+
theme_minimal() +
theme(axis.text=element_blank(),
axis.title=element_blank(),
legend.position="none")
In my case each vertex actually represents many points, where each vertex has a different number of points. Adding that information to gr.df:
gr.df$n <- NA
gr.df$n[which(is.na(gr.df$weight))] <- as.integer(runif(length(which(is.na(gr.df$weight))), 100, 500))
What I'd like to do is add to the plot gr.df$n radially jittered points around each vertex (i.e., with its corresponding n), with the same vertex.colors coding. Any idea how to do that?
I think sampling and then plotting with geom_point is a reasonable strategy. (otherwise you could create your own geom).
Here is some rough code, starting from the relevant bit of your question
gr.df$n <- 1
gr.df$n[which(is.na(gr.df$weight))] <- as.integer(runif(length(which(is.na(gr.df$weight))), 100, 500))
# function to sample
# https://stackoverflow.com/questions/5837572/generate-a-random-point-within-a-circle-uniformly
circSamp <- function(x, y, R=0.1){
n <- length(x)
A <- a <- runif(n,0,1)
b <- runif(n,0,1)
ind <- b < a
a[ind] <- b[ind]
b[ind] <- A[ind]
xn = x+b*R*cos(2*pi*a/b)
yn = y+b*R*sin(2*pi*a/b)
cbind(x=xn, y=yn)
}
# sample
d <- with(gr.df, data.frame(vertex.names=rep(vertex.names, n),
circSamp(rep(x,n), rep(y,n))))
# p is your plot
p + geom_point(data=d, aes(x, y, color = vertex.names),
alpha=0.1, inherit.aes = FALSE) +
scale_color_manual(values = vertex.colors)
Giving
I have a large dataset of gene expression from ~10,000 patient samples (TCGA), and I'm plotting a predicted expression value (x) and the actual observed value (y) of a certain gene signature. For my downstream analysis, I need to draw a precise line through the plot and calculate different parameters in samples above/below the line.
No matter how I draw a line through the data (geom_smooth(method = 'lm', 'glm', 'gam', or 'loess')), the line always seems imperfect - it doesn't cut through the data to my liking (red line is lm in figure).
After playing around for a while, I realized that the 2d kernel density lines (geom_density2d) actually do a good job of showing the slope/trends of my data, so I manually drew a line that kind of cuts through the density lines (black line in figure).
My question: how can I automatically draw a line that cuts through the kernel density lines, as for the black line in the figure? (Rather than manually playing with different intercepts and slopes till something looks good).
The best approach I can think of is to somehow calculate intercept and slope of the longest diameter for each of the kernel lines, take an average of all those intercepts and slopes and plot that line, but that's a bit out of my league. Maybe someone here has experience with this and can help?
A more hacky approach may be getting the x,y coords of each kernel density line from ggplot_build, and going from there, but it feels too hacky (and is also out of my league).
Thanks!
EDIT: Changed a few details to make the figure/analysis easier. (Density lines are smoother now).
Reprex:
library(MASS)
set.seed(123)
samples <- 10000
r <- 0.9
data <- mvrnorm(n=samples, mu=c(0, 0), Sigma=matrix(c(2, r, r, 2), nrow=2))
x <- data[, 1] # standard normal (mu=0, sd=1)
y <- data[, 2] # standard normal (mu=0, sd=1)
test.df <- data.frame(x = x, y = y)
lm(y ~ x, test.df)
ggplot(test.df, aes(x, y)) +
geom_point(color = 'grey') +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = c(2,2)) + ### EDIT: h = c(2,2)
geom_smooth(method = "glm", se = F, lwd = 1, color = 'red') +
geom_abline(intercept = 0, slope = 0.7, lwd = 1, col = 'black') ## EDIT: slope to 0.7
Figure:
I generally agree with #Hack-R.
However, it was kind of a fun problem and looking into ggplot_build is not such a big deal.
require(dplyr)
require(ggplot2)
p <- ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = c(2,2))
#basic version of your plot
p_built <- ggplot_build(p)
p_data <- p_built$data[[1]]
p_maxring <- p_data[p_data[['level']] == min(p_data[['level']]),] %>%
select(x,y) # extracts the x/y coordinates of the points on the largest ellipse from your 2d-density contour
Now this answer helped me to find the points on this ellipse which are furthest apart.
coord_mean <- c(x = mean(p_maxring$x), y = mean(p_maxring$y))
p_maxring <- p_maxring %>%
mutate (mean_dev = sqrt((x - mean(x))^2 + (y - mean(y))^2)) #extra column specifying the distance of each point to the mean of those points
coord_farthest <- c('x' = p_maxring$x[which.max(p_maxring$mean_dev)], 'y' = p_maxring$y[which.max(p_maxring$mean_dev)])
# gives the coordinates of the point farthest away from the mean point
farthest_from_farthest <- sqrt((p_maxring$x - coord_farthest['x'])^2 + (p_maxring$y - coord_farthest['y'])^2)
#now this looks which of the points is the farthest from the point farthest from the mean point :D
coord_fff <- c('x' = p_maxring$x[which.max(farthest_from_farthest)], 'y' = p_maxring$y[which.max(farthest_from_farthest)])
ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = c(2,2)) +
# geom_segment using the coordinates of the points farthest apart
geom_segment((aes(x = coord_farthest['x'], y = coord_farthest['y'],
xend = coord_fff['x'], yend = coord_fff['y']))) +
geom_smooth(method = "glm", se = F, lwd = 1, color = 'red') +
# as per your request with your geom_smooth line
coord_equal()
coord_equal is super important, because otherwise you will get super weird results - it messed up my brain too. Because if the coordinates are not set equal, the line will seemingly not pass through the point furthest apart from the mean...
I leave it to you to build this into a function in order to automate it. Also, I'll leave it to you to calculate the y-intercept and slope from the two points
Tjebo's approach was kind of good initially, but after a close look, I found that it found the longest distance between two points on an ellipse. While this is close to what I wanted, it failed with either an irregular shape of the ellipse, or the sparsity of points in the ellipse. This is because it measured the longest distance between two points; whereas what I really wanted is the longest diameter of an ellipse; i.e.: the semi-major axis. See image below for examples/details.
Briefly:
To find/draw density contours of specific density/percentage:
R - How to find points within specific Contour
To get the longest diameter ("semi-major axis") of an ellipse:
https://stackoverflow.com/a/18278767/3579613
For function that returns intercept and slope (as in OP), see last piece of code.
The two pieces of code and images below compare two Tjebo's approach vs. my new approach based on the above posts.
#### Reprex from OP
require(dplyr)
require(ggplot2)
require(MASS)
set.seed(123)
samples <- 10000
r <- 0.9
data <- mvrnorm(n=samples, mu=c(0, 0), Sigma=matrix(c(2, r, r, 2), nrow=2))
x <- data[, 1] # standard normal (mu=0, sd=1)
y <- data[, 2] # standard normal (mu=0, sd=1)
test.df <- data.frame(x = x, y = y)
#### From Tjebo
p <- ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = 2)
p_built <- ggplot_build(p)
p_data <- p_built$data[[1]]
p_maxring <- p_data[p_data[['level']] == min(p_data[['level']]),][,2:3]
coord_mean <- c(x = mean(p_maxring$x), y = mean(p_maxring$y))
p_maxring <- p_maxring %>%
mutate (mean_dev = sqrt((x - mean(x))^2 + (y - mean(y))^2)) #extra column specifying the distance of each point to the mean of those points
p_maxring = p_maxring[round(seq(1, nrow(p_maxring), nrow(p_maxring)/23)),] #### Make a small ellipse to illustrate flaws of approach
coord_farthest <- c('x' = p_maxring$x[which.max(p_maxring$mean_dev)], 'y' = p_maxring$y[which.max(p_maxring$mean_dev)])
# gives the coordinates of the point farthest away from the mean point
farthest_from_farthest <- sqrt((p_maxring$x - coord_farthest['x'])^2 + (p_maxring$y - coord_farthest['y'])^2)
#now this looks which of the points is the farthest from the point farthest from the mean point :D
coord_fff <- c('x' = p_maxring$x[which.max(farthest_from_farthest)], 'y' = p_maxring$y[which.max(farthest_from_farthest)])
farthest_2_points = data.frame(t(cbind(coord_farthest, coord_fff)))
plot(p_maxring[,1:2], asp=1)
lines(farthest_2_points, col = 'blue', lwd = 2)
#### From answer in another post
d = cbind(p_maxring[,1], p_maxring[,2])
r = ellipsoidhull(d)
exy = predict(r) ## the ellipsoid boundary
lines(exy)
me = colMeans((exy))
dist2center = sqrt(rowSums((t(t(exy)-me))^2))
max(dist2center) ## major axis
lines(exy[dist2center == max(dist2center),], col = 'red', lwd = 2)
#### The plot here is made from the data in the reprex in OP, but with h = 0.5
library(MASS)
set.seed(123)
samples <- 10000
r <- 0.9
data <- mvrnorm(n=samples, mu=c(0, 0), Sigma=matrix(c(2, r, r, 2), nrow=2))
x <- data[, 1] # standard normal (mu=0, sd=1)
y <- data[, 2] # standard normal (mu=0, sd=1)
test.df <- data.frame(x = x, y = y)
## MAKE BLUE LINE
p <- ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = 0.5) ## NOTE h = 0.5
p_built <- ggplot_build(p)
p_data <- p_built$data[[1]]
p_maxring <- p_data[p_data[['level']] == min(p_data[['level']]),][,2:3]
coord_mean <- c(x = mean(p_maxring$x), y = mean(p_maxring$y))
p_maxring <- p_maxring %>%
mutate (mean_dev = sqrt((x - mean(x))^2 + (y - mean(y))^2))
coord_farthest <- c('x' = p_maxring$x[which.max(p_maxring$mean_dev)], 'y' = p_maxring$y[which.max(p_maxring$mean_dev)])
farthest_from_farthest <- sqrt((p_maxring$x - coord_farthest['x'])^2 + (p_maxring$y - coord_farthest['y'])^2)
coord_fff <- c('x' = p_maxring$x[which.max(farthest_from_farthest)], 'y' = p_maxring$y[which.max(farthest_from_farthest)])
## MAKE RED LINE
## h = 0.5
## Given the highly irregular shape of the contours, I will use only the largest contour line (0.95) for draing the line.
## Thus, average = 1. See function below for details.
ln = long.diam("x", "y", test.df, h = 0.5, average = 1) ## NOTE h = 0.5
## PLOT
ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 0.5, contour = T, h = 0.5) + ## NOTE h = 0.5
geom_segment((aes(x = coord_farthest['x'], y = coord_farthest['y'],
xend = coord_fff['x'], yend = coord_fff['y'])), col = 'blue', lwd = 2) +
geom_abline(intercept = ln[1], slope = ln[2], color = 'red', lwd = 2) +
coord_equal()
Finally, I came up with the following function to deal with all this. Sorry for the lack of comments/clarity
#### This will return the intercept and slope of the longest diameter (semi-major axis).
####If Average = TRUE, it will average the int and slope across different density contours.
long.diam = function(x, y, df, probs = c(0.95, 0.5, 0.1), average = T, h = 2) {
fun.df = data.frame(cbind(df[,x], df[,y]))
colnames(fun.df) = c("x", "y")
dens = kde2d(fun.df$x, fun.df$y, n = 200, h = h)
dx <- diff(dens$x[1:2])
dy <- diff(dens$y[1:2])
sz <- sort(dens$z)
c1 <- cumsum(sz) * dx * dy
levels <- sapply(probs, function(x) {
approx(c1, sz, xout = 1 - x)$y
})
names(levels) = paste0("L", str_sub(formatC(probs, 2, format = 'f'), -2))
#plot(fun.df$x,fun.df$y, asp = 1)
#contour(dens, levels = levels, labels=probs, add=T, col = c('red', 'blue', 'green'), lwd = 2)
#contour(dens, add = T, col = 'red', lwd = 2)
#abline(lm(fun.df$y~fun.df$x))
ls <- contourLines(dens, levels = levels)
names(ls) = names(levels)
lines.info = list()
for (i in 1:length(ls)) {
d = cbind(ls[[i]]$x, ls[[i]]$y)
exy = predict(ellipsoidhull(d))## the ellipsoid boundary
colnames(exy) = c("x", "y")
me = colMeans((exy)) ## center of the ellipse
dist2center = sqrt(rowSums((t(t(exy)-me))^2))
#plot(exy,type='l',asp=1)
#points(d,col='blue')
#lines(exy[order(dist2center)[1:2],])
#lines(exy[rev(order(dist2center))[1:2],])
max.dist = data.frame(exy[rev(order(dist2center))[1:2],])
line.fit = lm(max.dist$y ~ max.dist$x)
lines.info[[i]] = c(as.numeric(line.fit$coefficients[1]), as.numeric(line.fit$coefficients[2]))
}
names(lines.info) = names(ls)
#plot(fun.df$x,fun.df$y, asp = 1)
#contour(dens, levels = levels, labels=probs, add=T, col = c('red', 'blue', 'green'), lwd = 2)
#abline(lines.info[[1]], col = 'red', lwd = 2)
#abline(lines.info[[2]], col = 'blue', lwd = 2)
#abline(lines.info[[3]], col = 'green', lwd = 2)
#abline(apply(simplify2array(lines.info), 1, mean), col = 'black', lwd = 4)
if (isTRUE(average)) {
apply(simplify2array(lines.info), 1, mean)
} else {
lines.info[[average]]
}
}
Finally, here's the final implementation of the different answers:
library(MASS)
set.seed(123)
samples = 10000
r = 0.9
data = mvrnorm(n=samples, mu=c(0, 0), Sigma=matrix(c(2, r, r, 2), nrow=2))
x = data[, 1] # standard normal (mu=0, sd=1)
y = data[, 2] # standard normal (mu=0, sd=1)
#plot(x, y)
test.df = data.frame(x = x, y = y)
#### Find furthest two points of contour
## BLUE
p <- ggplot(test.df, aes(x, y)) +
geom_density2d(color = 'red', lwd = 2, contour = T, h = 2)
p_built <- ggplot_build(p)
p_data <- p_built$data[[1]]
p_maxring <- p_data[p_data[['level']] == min(p_data[['level']]),][,2:3]
coord_mean <- c(x = mean(p_maxring$x), y = mean(p_maxring$y))
p_maxring <- p_maxring %>%
mutate (mean_dev = sqrt((x - mean(x))^2 + (y - mean(y))^2))
coord_farthest <- c('x' = p_maxring$x[which.max(p_maxring$mean_dev)], 'y' = p_maxring$y[which.max(p_maxring$mean_dev)])
farthest_from_farthest <- sqrt((p_maxring$x - coord_farthest['x'])^2 + (p_maxring$y - coord_farthest['y'])^2)
coord_fff <- c('x' = p_maxring$x[which.max(farthest_from_farthest)], 'y' = p_maxring$y[which.max(farthest_from_farthest)])
#### Find the average intercept and slope of 3 contour lines (0.95, 0.5, 0.1), as in my long.diam function above.
## RED
ln = long.diam("x", "y", test.df)
#### Plot everything. Black line is GLM
ggplot(test.df, aes(x, y)) +
geom_point(color = 'grey') +
geom_density2d(color = 'red', lwd = 1, contour = T, h = 2) +
geom_smooth(method = "glm", se = F, lwd = 1, color = 'black') +
geom_abline(intercept = ln[1], slope = ln[2], col = 'red', lwd = 1) +
geom_segment((aes(x = coord_farthest['x'], y = coord_farthest['y'],
xend = coord_fff['x'], yend = coord_fff['y'])), col = 'blue', lwd = 1) +
coord_equal()
I frequently use kernel density plots to illustrate distributions. These are easy and fast to create in R like so:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
#or in one line like this: plot(density(rnorm(100)^2))
Which gives me this nice little PDF:
I'd like to shade the area under the PDF from the 75th to 95th percentiles. It's easy to calculate the points using the quantile function:
q75 <- quantile(draws, .75)
q95 <- quantile(draws, .95)
But how do I shade the the area between q75 and q95?
With the polygon() function, see its help page and I believe we had similar questions here too.
You need to find the index of the quantile values to get the actual (x,y) pairs.
Edit: Here you go:
x1 <- min(which(dens$x >= q75))
x2 <- max(which(dens$x < q95))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
Output (added by JDL)
Another solution:
dd <- with(dens,data.frame(x,y))
library(ggplot2)
qplot(x,y,data=dd,geom="line")+
geom_ribbon(data=subset(dd,x>q75 & x<q95),aes(ymax=y),ymin=0,
fill="red",colour=NA,alpha=0.5)
Result:
An expanded solution:
If you wanted to shade both tails (copy & paste of Dirk's code) and use known x values:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
q2 <- 2
q65 <- 6.5
qn08 <- -0.8
qn02 <- -0.2
x1 <- min(which(dens$x >= q2))
x2 <- max(which(dens$x < q65))
x3 <- min(which(dens$x >= qn08))
x4 <- max(which(dens$x < qn02))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
with(dens, polygon(x=c(x[c(x3,x3:x4,x4)]), y= c(0, y[x3:x4], 0), col="gray"))
Result:
This question needs a lattice answer. Here's a very basic one, simply adapting the method employed by Dirk and others:
#Set up the data
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
#Put in a simple data frame
d <- data.frame(x = dens$x, y = dens$y)
#Define a custom panel function;
# Options like color don't need to be hard coded
shadePanel <- function(x,y,shadeLims){
panel.lines(x,y)
m1 <- min(which(x >= shadeLims[1]))
m2 <- max(which(x <= shadeLims[2]))
tmp <- data.frame(x1 = x[c(m1,m1:m2,m2)], y1 = c(0,y[m1:m2],0))
panel.polygon(tmp$x1,tmp$y1,col = "blue")
}
#Plot
xyplot(y~x,data = d, panel = shadePanel, shadeLims = c(1,3))
Here's another ggplot2 variant based on a function that approximates the kernel density at the original data values:
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
Using the original data (rather than producing a new data frame with the density estimate's x and y values) has the benefit of also working in faceted plots where the quantile values depend on the variable by which the data is being grouped:
Code used
library(tidyverse)
library(RColorBrewer)
# dummy data
set.seed(1)
n <- 1e2
dt <- tibble(value = rnorm(n)^2)
# function that approximates the density at the provided values
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
probs <- c(0.75, 0.95)
dt <- dt %>%
mutate(dy = approxdens(value), # calculate density
p = percent_rank(value), # percentile rank
pcat = as.factor(cut(p, breaks = probs, # percentile category based on probs
include.lowest = TRUE)))
ggplot(dt, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
scale_fill_brewer(guide = "none") +
theme_bw()
# dummy data with 2 groups
dt2 <- tibble(category = c(rep("A", n), rep("B", n)),
value = c(rnorm(n)^2, rnorm(n, mean = 2)))
dt2 <- dt2 %>%
group_by(category) %>%
mutate(dy = approxdens(value),
p = percent_rank(value),
pcat = as.factor(cut(p, breaks = probs,
include.lowest = TRUE)))
# faceted plot
ggplot(dt2, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
facet_wrap(~ category, nrow = 2, scales = "fixed") +
scale_fill_brewer(guide = "none") +
theme_bw()
Created on 2018-07-13 by the reprex package (v0.2.0).
I frequently use kernel density plots to illustrate distributions. These are easy and fast to create in R like so:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
#or in one line like this: plot(density(rnorm(100)^2))
Which gives me this nice little PDF:
I'd like to shade the area under the PDF from the 75th to 95th percentiles. It's easy to calculate the points using the quantile function:
q75 <- quantile(draws, .75)
q95 <- quantile(draws, .95)
But how do I shade the the area between q75 and q95?
With the polygon() function, see its help page and I believe we had similar questions here too.
You need to find the index of the quantile values to get the actual (x,y) pairs.
Edit: Here you go:
x1 <- min(which(dens$x >= q75))
x2 <- max(which(dens$x < q95))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
Output (added by JDL)
Another solution:
dd <- with(dens,data.frame(x,y))
library(ggplot2)
qplot(x,y,data=dd,geom="line")+
geom_ribbon(data=subset(dd,x>q75 & x<q95),aes(ymax=y),ymin=0,
fill="red",colour=NA,alpha=0.5)
Result:
An expanded solution:
If you wanted to shade both tails (copy & paste of Dirk's code) and use known x values:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
q2 <- 2
q65 <- 6.5
qn08 <- -0.8
qn02 <- -0.2
x1 <- min(which(dens$x >= q2))
x2 <- max(which(dens$x < q65))
x3 <- min(which(dens$x >= qn08))
x4 <- max(which(dens$x < qn02))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
with(dens, polygon(x=c(x[c(x3,x3:x4,x4)]), y= c(0, y[x3:x4], 0), col="gray"))
Result:
This question needs a lattice answer. Here's a very basic one, simply adapting the method employed by Dirk and others:
#Set up the data
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
#Put in a simple data frame
d <- data.frame(x = dens$x, y = dens$y)
#Define a custom panel function;
# Options like color don't need to be hard coded
shadePanel <- function(x,y,shadeLims){
panel.lines(x,y)
m1 <- min(which(x >= shadeLims[1]))
m2 <- max(which(x <= shadeLims[2]))
tmp <- data.frame(x1 = x[c(m1,m1:m2,m2)], y1 = c(0,y[m1:m2],0))
panel.polygon(tmp$x1,tmp$y1,col = "blue")
}
#Plot
xyplot(y~x,data = d, panel = shadePanel, shadeLims = c(1,3))
Here's another ggplot2 variant based on a function that approximates the kernel density at the original data values:
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
Using the original data (rather than producing a new data frame with the density estimate's x and y values) has the benefit of also working in faceted plots where the quantile values depend on the variable by which the data is being grouped:
Code used
library(tidyverse)
library(RColorBrewer)
# dummy data
set.seed(1)
n <- 1e2
dt <- tibble(value = rnorm(n)^2)
# function that approximates the density at the provided values
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
probs <- c(0.75, 0.95)
dt <- dt %>%
mutate(dy = approxdens(value), # calculate density
p = percent_rank(value), # percentile rank
pcat = as.factor(cut(p, breaks = probs, # percentile category based on probs
include.lowest = TRUE)))
ggplot(dt, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
scale_fill_brewer(guide = "none") +
theme_bw()
# dummy data with 2 groups
dt2 <- tibble(category = c(rep("A", n), rep("B", n)),
value = c(rnorm(n)^2, rnorm(n, mean = 2)))
dt2 <- dt2 %>%
group_by(category) %>%
mutate(dy = approxdens(value),
p = percent_rank(value),
pcat = as.factor(cut(p, breaks = probs,
include.lowest = TRUE)))
# faceted plot
ggplot(dt2, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
facet_wrap(~ category, nrow = 2, scales = "fixed") +
scale_fill_brewer(guide = "none") +
theme_bw()
Created on 2018-07-13 by the reprex package (v0.2.0).
I frequently use kernel density plots to illustrate distributions. These are easy and fast to create in R like so:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
#or in one line like this: plot(density(rnorm(100)^2))
Which gives me this nice little PDF:
I'd like to shade the area under the PDF from the 75th to 95th percentiles. It's easy to calculate the points using the quantile function:
q75 <- quantile(draws, .75)
q95 <- quantile(draws, .95)
But how do I shade the the area between q75 and q95?
With the polygon() function, see its help page and I believe we had similar questions here too.
You need to find the index of the quantile values to get the actual (x,y) pairs.
Edit: Here you go:
x1 <- min(which(dens$x >= q75))
x2 <- max(which(dens$x < q95))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
Output (added by JDL)
Another solution:
dd <- with(dens,data.frame(x,y))
library(ggplot2)
qplot(x,y,data=dd,geom="line")+
geom_ribbon(data=subset(dd,x>q75 & x<q95),aes(ymax=y),ymin=0,
fill="red",colour=NA,alpha=0.5)
Result:
An expanded solution:
If you wanted to shade both tails (copy & paste of Dirk's code) and use known x values:
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
plot(dens)
q2 <- 2
q65 <- 6.5
qn08 <- -0.8
qn02 <- -0.2
x1 <- min(which(dens$x >= q2))
x2 <- max(which(dens$x < q65))
x3 <- min(which(dens$x >= qn08))
x4 <- max(which(dens$x < qn02))
with(dens, polygon(x=c(x[c(x1,x1:x2,x2)]), y= c(0, y[x1:x2], 0), col="gray"))
with(dens, polygon(x=c(x[c(x3,x3:x4,x4)]), y= c(0, y[x3:x4], 0), col="gray"))
Result:
This question needs a lattice answer. Here's a very basic one, simply adapting the method employed by Dirk and others:
#Set up the data
set.seed(1)
draws <- rnorm(100)^2
dens <- density(draws)
#Put in a simple data frame
d <- data.frame(x = dens$x, y = dens$y)
#Define a custom panel function;
# Options like color don't need to be hard coded
shadePanel <- function(x,y,shadeLims){
panel.lines(x,y)
m1 <- min(which(x >= shadeLims[1]))
m2 <- max(which(x <= shadeLims[2]))
tmp <- data.frame(x1 = x[c(m1,m1:m2,m2)], y1 = c(0,y[m1:m2],0))
panel.polygon(tmp$x1,tmp$y1,col = "blue")
}
#Plot
xyplot(y~x,data = d, panel = shadePanel, shadeLims = c(1,3))
Here's another ggplot2 variant based on a function that approximates the kernel density at the original data values:
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
Using the original data (rather than producing a new data frame with the density estimate's x and y values) has the benefit of also working in faceted plots where the quantile values depend on the variable by which the data is being grouped:
Code used
library(tidyverse)
library(RColorBrewer)
# dummy data
set.seed(1)
n <- 1e2
dt <- tibble(value = rnorm(n)^2)
# function that approximates the density at the provided values
approxdens <- function(x) {
dens <- density(x)
f <- with(dens, approxfun(x, y))
f(x)
}
probs <- c(0.75, 0.95)
dt <- dt %>%
mutate(dy = approxdens(value), # calculate density
p = percent_rank(value), # percentile rank
pcat = as.factor(cut(p, breaks = probs, # percentile category based on probs
include.lowest = TRUE)))
ggplot(dt, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
scale_fill_brewer(guide = "none") +
theme_bw()
# dummy data with 2 groups
dt2 <- tibble(category = c(rep("A", n), rep("B", n)),
value = c(rnorm(n)^2, rnorm(n, mean = 2)))
dt2 <- dt2 %>%
group_by(category) %>%
mutate(dy = approxdens(value),
p = percent_rank(value),
pcat = as.factor(cut(p, breaks = probs,
include.lowest = TRUE)))
# faceted plot
ggplot(dt2, aes(value, dy)) +
geom_ribbon(aes(ymin = 0, ymax = dy, fill = pcat)) +
geom_line() +
facet_wrap(~ category, nrow = 2, scales = "fixed") +
scale_fill_brewer(guide = "none") +
theme_bw()
Created on 2018-07-13 by the reprex package (v0.2.0).