Related
I am trying to plot two variables where N=700K. The problem is that there is too much overlap, so that the plot becomes mostly a solid block of black. Is there any way of having a grayscale "cloud" where the darkness of the plot is a function of the number of points in an region? In other words, instead of showing individual points, I want the plot to be a "cloud", with the more the number of points in a region, the darker that region.
One way to deal with this is with alpha blending, which makes each point slightly transparent. So regions appear darker that have more point plotted on them.
This is easy to do in ggplot2:
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
ggplot(df,aes(x=x,y=y)) + geom_point(alpha = 0.3)
Another convenient way to deal with this is (and probably more appropriate for the number of points you have) is hexagonal binning:
ggplot(df,aes(x=x,y=y)) + stat_binhex()
And there is also regular old rectangular binning (image omitted), which is more like your traditional heatmap:
ggplot(df,aes(x=x,y=y)) + geom_bin2d()
An overview of several good options in ggplot2:
library(ggplot2)
x <- rnorm(n = 10000)
y <- rnorm(n = 10000, sd=2) + x
df <- data.frame(x, y)
Option A: transparent points
o1 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05)
Option B: add density contours
o2 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05) +
geom_density_2d()
Option C: add filled density contours
(Note that the points distort the perception of the colors underneath, may be better without points.)
o3 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(level)), geom = 'polygon') +
scale_fill_viridis_c(name = "density") +
geom_point(shape = '.')
Option D: density heatmap
(Same note as C.)
o4 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(density)), geom = 'raster', contour = FALSE) +
scale_fill_viridis_c() +
coord_cartesian(expand = FALSE) +
geom_point(shape = '.', col = 'white')
Option E: hexbins
(Same note as C.)
o5 <- ggplot(df, aes(x, y)) +
geom_hex() +
scale_fill_viridis_c() +
geom_point(shape = '.', col = 'white')
Option F: rugs
Possibly my favorite option. Not quite as flashy, but visually simple and simple to understand. Very effective in many cases.
o6 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.1) +
geom_rug(alpha = 0.01)
Combine in one figure:
cowplot::plot_grid(
o1, o2, o3, o4, o5, o6,
ncol = 2, labels = 'AUTO', align = 'v', axis = 'lr'
)
You can also have a look at the ggsubplot package. This package implements features which were presented by Hadley Wickham back in 2011 (http://blog.revolutionanalytics.com/2011/10/ggplot2-for-big-data.html).
(In the following, I include the "points"-layer for illustration purposes.)
library(ggplot2)
library(ggsubplot)
# Make up some data
set.seed(955)
dat <- data.frame(cond = rep(c("A", "B"), each=5000),
xvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)),
yvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)))
# Scatterplot with subplots (simple)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(rep("dummy", length(xvar)), ..count..))), bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
However, this features rocks if you have a third variable to control for.
# Scatterplot with subplots (including a third variable)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1, aes(color = factor(cond))) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(cond, ..count.., fill = cond))),
bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
Or another approach would be to use smoothScatter():
smoothScatter(dat[2:3])
Alpha blending is easy to do with base graphics as well.
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
with(df, plot(x, y, col="#00000033"))
The first six numbers after the # are the color in RGB hex and the last two are the opacity, again in hex, so 33 ~ 3/16th opaque.
You can also use density contour lines (ggplot2):
df <- data.frame(x = rnorm(15000),y=rnorm(15000))
ggplot(df,aes(x=x,y=y)) + geom_point() + geom_density2d()
Or combine density contours with alpha blending:
ggplot(df,aes(x=x,y=y)) +
geom_point(colour="blue", alpha=0.2) +
geom_density2d(colour="black")
You may find useful the hexbin package. From the help page of hexbinplot:
library(hexbin)
mixdata <- data.frame(x = c(rnorm(5000),rnorm(5000,4,1.5)),
y = c(rnorm(5000),rnorm(5000,2,3)),
a = gl(2, 5000))
hexbinplot(y ~ x | a, mixdata)
geom_pointdenisty from the ggpointdensity package (recently developed by Lukas Kremer and Simon Anders (2019)) allows you visualize density and individual data points at the same time:
library(ggplot2)
# install.packages("ggpointdensity")
library(ggpointdensity)
df <- data.frame(x = rnorm(5000), y = rnorm(5000))
ggplot(df, aes(x=x, y=y)) + geom_pointdensity() + scale_color_viridis_c()
My favorite method for plotting this type of data is the one described in this question - a scatter-density plot. The idea is to do a scatter-plot but to colour the points by their density (roughly speaking, the amount of overlap in that area).
It simultaneously:
clearly shows the location of outliers, and
reveals any structure in the dense area of the plot.
Here is the result from the top answer to the linked question:
Please pardon my ignorance if this is a simple question, but I can't seem to figure out how to underline any part of a plot title. I'm using ggplot2.
The best I could find was
annotate("segment") done by hand, and I have created a toy plot to illustrate its method.
df <- data.frame(x = 1:10, y = 1:10)
rngx <- 0.5 * range(df$x)[2] # store mid-point of plot based on x-axis value
rngy <- 0.5 * range(df$y)[2] # stores mid-point of y-axis for use in ggplot
ggplot(df, aes(x = x, y = y)) +
geom_point() +
ggtitle("Oh how I wish for ..." ) +
ggplot2::annotate("text", x = rngx, y = max(df$y) + 1, label = "underlining!", color = "red") +
# create underline:
ggplot2::annotate("segment", x = rngx-0.8, xend = rngx + 0.8, y= 10.1, yend=10.1)
uses bquote(underline() with base R
pertains to lines over and under nodes on a graph
uses plotmath and offers a workaround, but it didn't help
Try this:
ggplot(df, aes(x = x, y = y)) + geom_point() +
ggtitle(expression(paste("Oh how I wish for ", underline(underlining))))
Alternatively, as BondedDust points out in the comments, you can avoid the paste() call entirely, but watch out for the for:
ggplot(df, aes(x = x, y = y)) + geom_point() +
ggtitle(expression(Oh~how~I~wish~'for'~underline(underlining)))
Or another, even shorter approach suggested by baptiste that doesn't use expression, paste(), or the many tildes:
ggplot(df, aes(x = x, y = y)) + geom_point() +
ggtitle(~"Oh how I wish for "*underline(underlining))
I am trying to plot two variables where N=700K. The problem is that there is too much overlap, so that the plot becomes mostly a solid block of black. Is there any way of having a grayscale "cloud" where the darkness of the plot is a function of the number of points in an region? In other words, instead of showing individual points, I want the plot to be a "cloud", with the more the number of points in a region, the darker that region.
One way to deal with this is with alpha blending, which makes each point slightly transparent. So regions appear darker that have more point plotted on them.
This is easy to do in ggplot2:
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
ggplot(df,aes(x=x,y=y)) + geom_point(alpha = 0.3)
Another convenient way to deal with this is (and probably more appropriate for the number of points you have) is hexagonal binning:
ggplot(df,aes(x=x,y=y)) + stat_binhex()
And there is also regular old rectangular binning (image omitted), which is more like your traditional heatmap:
ggplot(df,aes(x=x,y=y)) + geom_bin2d()
An overview of several good options in ggplot2:
library(ggplot2)
x <- rnorm(n = 10000)
y <- rnorm(n = 10000, sd=2) + x
df <- data.frame(x, y)
Option A: transparent points
o1 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05)
Option B: add density contours
o2 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05) +
geom_density_2d()
Option C: add filled density contours
(Note that the points distort the perception of the colors underneath, may be better without points.)
o3 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(level)), geom = 'polygon') +
scale_fill_viridis_c(name = "density") +
geom_point(shape = '.')
Option D: density heatmap
(Same note as C.)
o4 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(density)), geom = 'raster', contour = FALSE) +
scale_fill_viridis_c() +
coord_cartesian(expand = FALSE) +
geom_point(shape = '.', col = 'white')
Option E: hexbins
(Same note as C.)
o5 <- ggplot(df, aes(x, y)) +
geom_hex() +
scale_fill_viridis_c() +
geom_point(shape = '.', col = 'white')
Option F: rugs
Possibly my favorite option. Not quite as flashy, but visually simple and simple to understand. Very effective in many cases.
o6 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.1) +
geom_rug(alpha = 0.01)
Combine in one figure:
cowplot::plot_grid(
o1, o2, o3, o4, o5, o6,
ncol = 2, labels = 'AUTO', align = 'v', axis = 'lr'
)
You can also have a look at the ggsubplot package. This package implements features which were presented by Hadley Wickham back in 2011 (http://blog.revolutionanalytics.com/2011/10/ggplot2-for-big-data.html).
(In the following, I include the "points"-layer for illustration purposes.)
library(ggplot2)
library(ggsubplot)
# Make up some data
set.seed(955)
dat <- data.frame(cond = rep(c("A", "B"), each=5000),
xvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)),
yvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)))
# Scatterplot with subplots (simple)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(rep("dummy", length(xvar)), ..count..))), bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
However, this features rocks if you have a third variable to control for.
# Scatterplot with subplots (including a third variable)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1, aes(color = factor(cond))) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(cond, ..count.., fill = cond))),
bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
Or another approach would be to use smoothScatter():
smoothScatter(dat[2:3])
Alpha blending is easy to do with base graphics as well.
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
with(df, plot(x, y, col="#00000033"))
The first six numbers after the # are the color in RGB hex and the last two are the opacity, again in hex, so 33 ~ 3/16th opaque.
You can also use density contour lines (ggplot2):
df <- data.frame(x = rnorm(15000),y=rnorm(15000))
ggplot(df,aes(x=x,y=y)) + geom_point() + geom_density2d()
Or combine density contours with alpha blending:
ggplot(df,aes(x=x,y=y)) +
geom_point(colour="blue", alpha=0.2) +
geom_density2d(colour="black")
You may find useful the hexbin package. From the help page of hexbinplot:
library(hexbin)
mixdata <- data.frame(x = c(rnorm(5000),rnorm(5000,4,1.5)),
y = c(rnorm(5000),rnorm(5000,2,3)),
a = gl(2, 5000))
hexbinplot(y ~ x | a, mixdata)
geom_pointdenisty from the ggpointdensity package (recently developed by Lukas Kremer and Simon Anders (2019)) allows you visualize density and individual data points at the same time:
library(ggplot2)
# install.packages("ggpointdensity")
library(ggpointdensity)
df <- data.frame(x = rnorm(5000), y = rnorm(5000))
ggplot(df, aes(x=x, y=y)) + geom_pointdensity() + scale_color_viridis_c()
My favorite method for plotting this type of data is the one described in this question - a scatter-density plot. The idea is to do a scatter-plot but to colour the points by their density (roughly speaking, the amount of overlap in that area).
It simultaneously:
clearly shows the location of outliers, and
reveals any structure in the dense area of the plot.
Here is the result from the top answer to the linked question:
A ggplot2-challenged latticist needs help: What's the syntax to request variable per-facet breaks in a histogram?
library(ggplot2)
d = data.frame(x=c(rnorm(100,10,0.1),rnorm(100,20,0.1)),par=rep(letters[1:2],each=100))
# Note: breaks have different length by par
breaks = list(a=seq(9,11,by=0.1),b=seq(19,21,by=0.2))
ggplot(d, aes(x=x) ) +
geom_histogram() + ### Here the ~breaks should be added
facet_wrap(~ par, scales="free")
As pointed out by jucor, here some more solutions.
On special request, and to show why I am not a great ggplot fan, the lattice version
library(lattice)
d = data.frame(x=c(rnorm(100,10,0.1),rnorm(100,20,0.1)),par=rep(letters[1:2],each=100))
# Note: breaks have different length by par
myBreaks = list(a=seq(8,12,by=0.1),b=seq(18,22,by=0.2))
histogram(~x|par,data=d,
panel = function(x,breaks,...){
# I don't know of a generic way to get the
# grouping variable with histogram, so
# this is not very generic
par = levels(d$par)[which.packet()]
breaks = myBreaks[[par]]
panel.histogram(x,breaks=breaks,...)
},
breaks=NULL, # important to force per-panel compute
scales=list(x=list(relation="free")))
Here is one alternative:
hls <- mapply(function(x, b) geom_histogram(data = x, breaks = b),
dlply(d, .(par)), myBreaks)
ggplot(d, aes(x=x)) + hls + facet_wrap(~par, scales = "free_x")
If you need to shrink the range of x, then
hls <- mapply(function(x, b) {
rng <- range(x$x)
bb <- c(rng[1], b[rng[1] <= b & b <= rng[2]], rng[2])
geom_histogram(data = x, breaks = bb, colour = "white")
}, dlply(d, .(par)), myBreaks)
ggplot(d, aes(x=x)) + hls + facet_wrap(~par, scales = "free_x")
I don't think that it is possible to give different break points in each facet.
As workaround you can make two plots and then with grid.arrange() function from library gridExtra put them together. To set break points in geom_histogram() use binwidth= and set one value for width of bin.
p1<-ggplot(subset(d,par=="a"), aes(x=x) ) +
geom_histogram(binwidth=0.1) +
facet_wrap(~ par)
p2<-ggplot(subset(d,par=="b"), aes(x=x) ) +
geom_histogram(binwidth=0.2) +
facet_wrap(~ par)
library(gridExtra)
grid.arrange(p1,p2,ncol=2)
Following on from Didzis example:
ggplot(dat=d, aes(x=x, y=..ncount..)) +
geom_histogram(data = d[d$par == "a",], binwidth=0.1) +
geom_histogram(data = d[d$par == "b",], binwidth=0.01) +
facet_grid(.~ par, scales="free")
EDIT: This works for more levels but of course there are already better solutions
# More facets
d <- data.frame(x=c(rnorm(200,10,0.1),rnorm(200,20,0.1)),par=rep(letters[1:4],each=100))
# vector of binwidths same length as number of facets - need a nicer way to calculate these
my.width=c(0.5,0.25,0.1,0.01)
out<-lapply(1:length(my.width),function(.i) data.frame(par=levels(d$par)[.i],ggplot2:::bin(d$x[d$par==levels(d$par)[.i]],binwidth=my.width[.i])))
my.df<-do.call(rbind , out)
ggplot(my.df) + geom_histogram(aes(x, y = density, width = width), stat = "identity") + facet_wrap(~par,scales="free")
from https://groups.google.com/forum/?fromgroups=#!searchin/ggplot2/bin$20histogram$20by$20facet/ggplot2/xlqRIFPP-zE/CgfigIkgAAkJ
It is not, strictly speaking, possible to give different breaks in the different facets. But you can get the same effect by having a different layer for each facet (much as in user20650's answer), but mostly automating the multiple geom_histogram calls:
d <- data.frame(x=c(rnorm(100,10,0.1),rnorm(100,20,0.1)),
par=rep(letters[1:2],each=100))
breaks <- list(a=seq(9,11,by=0.1),b=seq(19,21,by=0.2))
ggplot(d, aes(x=x)) +
mapply(function(d, b) {geom_histogram(data=d, breaks=b)},
split(d, d$par), breaks) +
facet_wrap(~ par, scales="free_x")
The mapply call creates a list of geom_histograms which can be added to the plot. The tricky part is that you have to manually split the data (split(d, d$par)) into the data that goes into each facet.
I am trying to plot two variables where N=700K. The problem is that there is too much overlap, so that the plot becomes mostly a solid block of black. Is there any way of having a grayscale "cloud" where the darkness of the plot is a function of the number of points in an region? In other words, instead of showing individual points, I want the plot to be a "cloud", with the more the number of points in a region, the darker that region.
One way to deal with this is with alpha blending, which makes each point slightly transparent. So regions appear darker that have more point plotted on them.
This is easy to do in ggplot2:
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
ggplot(df,aes(x=x,y=y)) + geom_point(alpha = 0.3)
Another convenient way to deal with this is (and probably more appropriate for the number of points you have) is hexagonal binning:
ggplot(df,aes(x=x,y=y)) + stat_binhex()
And there is also regular old rectangular binning (image omitted), which is more like your traditional heatmap:
ggplot(df,aes(x=x,y=y)) + geom_bin2d()
An overview of several good options in ggplot2:
library(ggplot2)
x <- rnorm(n = 10000)
y <- rnorm(n = 10000, sd=2) + x
df <- data.frame(x, y)
Option A: transparent points
o1 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05)
Option B: add density contours
o2 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.05) +
geom_density_2d()
Option C: add filled density contours
(Note that the points distort the perception of the colors underneath, may be better without points.)
o3 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(level)), geom = 'polygon') +
scale_fill_viridis_c(name = "density") +
geom_point(shape = '.')
Option D: density heatmap
(Same note as C.)
o4 <- ggplot(df, aes(x, y)) +
stat_density_2d(aes(fill = stat(density)), geom = 'raster', contour = FALSE) +
scale_fill_viridis_c() +
coord_cartesian(expand = FALSE) +
geom_point(shape = '.', col = 'white')
Option E: hexbins
(Same note as C.)
o5 <- ggplot(df, aes(x, y)) +
geom_hex() +
scale_fill_viridis_c() +
geom_point(shape = '.', col = 'white')
Option F: rugs
Possibly my favorite option. Not quite as flashy, but visually simple and simple to understand. Very effective in many cases.
o6 <- ggplot(df, aes(x, y)) +
geom_point(alpha = 0.1) +
geom_rug(alpha = 0.01)
Combine in one figure:
cowplot::plot_grid(
o1, o2, o3, o4, o5, o6,
ncol = 2, labels = 'AUTO', align = 'v', axis = 'lr'
)
You can also have a look at the ggsubplot package. This package implements features which were presented by Hadley Wickham back in 2011 (http://blog.revolutionanalytics.com/2011/10/ggplot2-for-big-data.html).
(In the following, I include the "points"-layer for illustration purposes.)
library(ggplot2)
library(ggsubplot)
# Make up some data
set.seed(955)
dat <- data.frame(cond = rep(c("A", "B"), each=5000),
xvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)),
yvar = c(rep(1:20,250) + rnorm(5000,sd=5),rep(16:35,250) + rnorm(5000,sd=5)))
# Scatterplot with subplots (simple)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(rep("dummy", length(xvar)), ..count..))), bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
However, this features rocks if you have a third variable to control for.
# Scatterplot with subplots (including a third variable)
ggplot(dat, aes(x=xvar, y=yvar)) +
geom_point(shape=1, aes(color = factor(cond))) +
geom_subplot2d(aes(xvar, yvar,
subplot = geom_bar(aes(cond, ..count.., fill = cond))),
bins = c(15,15), ref = NULL, width = rel(0.8), ply.aes = FALSE)
Or another approach would be to use smoothScatter():
smoothScatter(dat[2:3])
Alpha blending is easy to do with base graphics as well.
df <- data.frame(x = rnorm(5000),y=rnorm(5000))
with(df, plot(x, y, col="#00000033"))
The first six numbers after the # are the color in RGB hex and the last two are the opacity, again in hex, so 33 ~ 3/16th opaque.
You can also use density contour lines (ggplot2):
df <- data.frame(x = rnorm(15000),y=rnorm(15000))
ggplot(df,aes(x=x,y=y)) + geom_point() + geom_density2d()
Or combine density contours with alpha blending:
ggplot(df,aes(x=x,y=y)) +
geom_point(colour="blue", alpha=0.2) +
geom_density2d(colour="black")
You may find useful the hexbin package. From the help page of hexbinplot:
library(hexbin)
mixdata <- data.frame(x = c(rnorm(5000),rnorm(5000,4,1.5)),
y = c(rnorm(5000),rnorm(5000,2,3)),
a = gl(2, 5000))
hexbinplot(y ~ x | a, mixdata)
geom_pointdenisty from the ggpointdensity package (recently developed by Lukas Kremer and Simon Anders (2019)) allows you visualize density and individual data points at the same time:
library(ggplot2)
# install.packages("ggpointdensity")
library(ggpointdensity)
df <- data.frame(x = rnorm(5000), y = rnorm(5000))
ggplot(df, aes(x=x, y=y)) + geom_pointdensity() + scale_color_viridis_c()
My favorite method for plotting this type of data is the one described in this question - a scatter-density plot. The idea is to do a scatter-plot but to colour the points by their density (roughly speaking, the amount of overlap in that area).
It simultaneously:
clearly shows the location of outliers, and
reveals any structure in the dense area of the plot.
Here is the result from the top answer to the linked question: