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:
New to programming and first time post.
I'm trying to create a stacked bubble chart to display how a population breaks down into it's proportions. My aim is to write this as a function so that I can use it repeatedly easily, but I need to get the meat of the code sorted before turning it to a function.
This is the type of plot I would like:
This is the code I've tried so far:
library(ggplot2)
# some data
observations = c(850, 500, 200, 50)
plot_data = data.frame(
"x" = rep.int(1,length(observations))
,"y" = rep.int(1,length(observations))
, "size" = rep.int(1,length(observations))
,"colour" = c(1:length(observations))
)
# convert to percentage for relative sizes
for (i in 1:length(observations))
{
plot_data$size[i] = (observations[i]/max(observations))*100
}
ggplot(plot_data,aes(x = x, y = y)) +
geom_point(aes(size = size, color = colour)) +
scale_size_identity() +
scale_y_continuous (limits = c(0.5, 1.5)) +
theme(legend.position = "none")
This produces a bullseye type image.
My approach has been to try and work out how the circle radii are calculated, and then update the y value in the for loop for each entry such that all the circles touch at the base - this is where I have been failing.
So my question:
How can I work out what the y coordinates for each circle needs to be?
Thank you for any help and hints.
I think this simplifies the answer that Henrick found:
circle <- function(center, radius, group) {
th <- seq(0, 2*pi, len=200)
data.frame(group=group,
x=center[1] + radius*cos(th),
y=center[2] + radius*sin(th))
}
# Create a named vector for your values
obs <- c(Org1=500, Org2=850, Org3=50, Org4=200)
# this reverse sorts them (so the stacked layered circles work)
# and makes it a list
obs <- as.list(rev(sort(obs)))
# need the radii
rads <- lapply(obs, "/", 2)
# need the max
x <- max(sapply(rads, "["))
# build a data frame of created circles
do.call(rbind.data.frame, lapply(1:length(rads), function(i) {
circle(c(x, rads[[i]]), rads[[i]], names(rads[i]))
})) -> dat
# make the plot
gg <- ggplot(dat)
gg <- gg + geom_polygon(aes(x=x, y=y, group=group, fill=group),
color="black")
gg <- gg + coord_equal()
gg <- gg + ggthemes::theme_map()
gg <- gg + theme(legend.position="right")
gg
You can tweak the guides/colors with standard ggplot functions.
This question already has answers here:
Align multiple plots in ggplot2 when some have legends and others don't
(6 answers)
Closed 5 years ago.
I'm trying to use ggplot to draw a graph comparing the absolute values of two variables, and also show the ratio between them. Since the ratio is unitless and the values are not, I can't show them on the same y-axis, so I'd like to stack vertically as two separate graphs with aligned x-axes.
Here's what I've got so far:
library(ggplot2)
library(dplyr)
library(gridExtra)
# Prepare some sample data.
results <- data.frame(index=(1:20))
results$control <- 50 * results$index
results$value <- results$index * 50 + 2.5*results$index^2 - results$index^3 / 8
results$ratio <- results$value / results$control
# Plot absolute values
plot_values <- ggplot(results, aes(x=index)) +
geom_point(aes(y=value, color="value")) +
geom_point(aes(y=control, color="control"))
# Plot ratios between values
plot_ratios <- ggplot(results, aes(x=index, y=ratio)) +
geom_point()
# Arrange the two plots above each other
grid.arrange(plot_values, plot_ratios, ncol=1, nrow=2)
The big problem is that the legend on the right of the first plot makes it a different size. A minor problem is that I'd rather not show the x-axis name and tick marks on the top plot, to avoid clutter and make it clear that they share the same axis.
I've looked at this question and its answers:
Align plot areas in ggplot
Unfortunately, neither answer there works well for me. Faceting doesn't seem a good fit, since I want to have completely different y scales for my two graphs. Manipulating the dimensions returned by ggplot_gtable seems more promising, but I don't know how to get around the fact that the two graphs have a different number of cells. Naively copying that code doesn't seem to change the resulting graph dimensions for my case.
Here's another similar question:
The perils of aligning plots in ggplot
The question itself seems to suggest a good option, but rbind.gtable complains if the tables have different numbers of columns, which is the case here due to the legend. Perhaps there's a way to slot in an extra empty column in the second table? Or a way to suppress the legend in the first graph and then re-add it to the combined graph?
Here's a solution that doesn't require explicit use of grid graphics. It uses facets, and hides the legend entry for "ratio" (using a technique from https://stackoverflow.com/a/21802022).
library(reshape2)
results_long <- melt(results, id.vars="index")
results_long$facet <- ifelse(results_long$variable=="ratio", "ratio", "values")
results_long$facet <- factor(results_long$facet, levels=c("values", "ratio"))
ggplot(results_long, aes(x=index, y=value, colour=variable)) +
geom_point() +
facet_grid(facet ~ ., scales="free_y") +
scale_colour_manual(breaks=c("control","value"),
values=c("#1B9E77", "#D95F02", "#7570B3")) +
theme(legend.justification=c(0,1), legend.position=c(0,1)) +
guides(colour=guide_legend(title=NULL)) +
theme(axis.title.y = element_blank())
Try this:
library(ggplot2)
library(gtable)
library(gridExtra)
AlignPlots <- function(...) {
LegendWidth <- function(x) x$grobs[[8]]$grobs[[1]]$widths[[4]]
plots.grobs <- lapply(list(...), ggplotGrob)
max.widths <- do.call(unit.pmax, lapply(plots.grobs, "[[", "widths"))
plots.grobs.eq.widths <- lapply(plots.grobs, function(x) {
x$widths <- max.widths
x
})
legends.widths <- lapply(plots.grobs, LegendWidth)
max.legends.width <- do.call(max, legends.widths)
plots.grobs.eq.widths.aligned <- lapply(plots.grobs.eq.widths, function(x) {
if (is.gtable(x$grobs[[8]])) {
x$grobs[[8]] <- gtable_add_cols(x$grobs[[8]],
unit(abs(diff(c(LegendWidth(x),
max.legends.width))),
"mm"))
}
x
})
plots.grobs.eq.widths.aligned
}
df <- data.frame(x = c(1:5, 1:5),
y = c(1:5, seq.int(5,1)),
type = factor(c(rep_len("t1", 5), rep_len("t2", 5))))
p1.1 <- ggplot(diamonds, aes(clarity, fill = cut)) + geom_bar()
p1.2 <- ggplot(df, aes(x = x, y = y, colour = type)) + geom_line()
plots1 <- AlignPlots(p1.1, p1.2)
do.call(grid.arrange, plots1)
p2.1 <- ggplot(diamonds, aes(clarity, fill = cut)) + geom_bar()
p2.2 <- ggplot(df, aes(x = x, y = y)) + geom_line()
plots2 <- AlignPlots(p2.1, p2.2)
do.call(grid.arrange, plots2)
Produces this:
// Based on multiple baptiste's answers
Encouraged by baptiste's comment, here's what I did in the end:
library(ggplot2)
library(dplyr)
library(gridExtra)
# Prepare some sample data.
results <- data.frame(index=(1:20))
results$control <- 50 * results$index
results$value <- results$index * 50 + 2.5*results$index^2 - results$index^3 / 8
results$ratio <- results$value / results$control
# Plot ratios between values
plot_ratios <- ggplot(results, aes(x=index, y=ratio)) +
geom_point()
# Plot absolute values
remove_x_axis =
theme(
axis.ticks.x = element_blank(),
axis.text.x = element_blank(),
axis.title.x = element_blank())
plot_values <- ggplot(results, aes(x=index)) +
geom_point(aes(y=value, color="value")) +
geom_point(aes(y=control, color="control")) +
remove_x_axis
# Arrange the two plots above each other
grob_ratios <- ggplotGrob(plot_ratios)
grob_values <- ggplotGrob(plot_values)
legend_column <- 5
legend_width <- grob_values$widths[legend_column]
grob_ratios <- gtable_add_cols(grob_ratios, legend_width, legend_column-1)
grob_combined <- gtable:::rbind_gtable(grob_values, grob_ratios, "first")
grob_combined <- gtable_add_rows(
grob_combined,unit(-1.2,"cm"), pos=nrow(grob_values))
grid.draw(grob_combined)
(I later realised I didn't even need to extract the legend width, since the size="first" argument to rbind tells it just to have that one override the other.)
It feels a bit messy, but it is exactly the layout I was hoping for.
An alternative & quite easy solution is as follows:
# loading needed packages
library(ggplot2)
library(dplyr)
library(tidyr)
# Prepare some sample data
results <- data.frame(index=(1:20))
results$control <- 50 * results$index
results$value <- results$index * 50 + 2.5*results$index^2 - results$index^3 / 8
results$ratio <- results$value / results$control
# reshape into long format
long <- results %>%
gather(variable, value, -index) %>%
mutate(facet = ifelse(variable=="ratio", "ratio", "values"))
long$facet <- factor(long$facet, levels=c("values", "ratio"))
# create the plot & remove facet labels with theme() elements
ggplot(long, aes(x=index, y=value, colour=variable)) +
geom_point() +
facet_grid(facet ~ ., scales="free_y") +
scale_colour_manual(breaks=c("control","value"), values=c("green", "red", "blue")) +
theme(axis.title.y=element_blank(), strip.text=element_blank(), strip.background=element_blank())
which gives:
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:
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: