如何在R中绘制两个直方图?

你链接的图片是密度曲线，不是直方图。

如果您一直在阅读ggplot，那么可能您唯一缺少的是将两个数据帧合并为一个长数据帧。

那么，让我们从你拥有的两组独立的数据开始，并将它们结合起来。

carrots <- data.frame(length = rnorm(100000, 6, 2))
cukes <- data.frame(length = rnorm(50000, 7, 2.5))


# Now, combine your two dataframes into one.
# First make a new column in each that will be
# a variable to identify where they came from later.
carrots$veg <- 'carrot'
cukes$veg <- 'cuke'


# and combine into your new data frame vegLengths
vegLengths <- rbind(carrots, cukes)

在那之后，如果你的数据已经是长格式的，这是不必要的，你只需要一行来绘制你的图表。

ggplot(vegLengths, aes(length, fill = veg)) + geom_density(alpha = 0.2)

现在，如果你真的想要直方图，下面的方法就可以了。注意，必须从默认的"stack"参数更改位置。如果您不知道您的数据应该是什么样子，您可能会错过这一点。更高的alpha看起来更好。还要注意，我把它做成了密度直方图。很容易删除y = ..density..以使其返回counts。

ggplot(vegLengths, aes(length, fill = veg)) +
geom_histogram(alpha = 0.5, aes(y = ..density..), position = 'identity')

下面是一个在“经典”R图形中如何做到这一点的例子:

## generate some random data
carrotLengths <- rnorm(1000,15,5)
cucumberLengths <- rnorm(200,20,7)
## calculate the histograms - don't plot yet
histCarrot <- hist(carrotLengths,plot = FALSE)
histCucumber <- hist(cucumberLengths,plot = FALSE)
## calculate the range of the graph
xlim <- range(histCucumber$breaks,histCarrot$breaks)
ylim <- range(0,histCucumber$density,
histCarrot$density)
## plot the first graph
plot(histCarrot,xlim = xlim, ylim = ylim,
col = rgb(1,0,0,0.4),xlab = 'Lengths',
freq = FALSE, ## relative, not absolute frequency
main = 'Distribution of carrots and cucumbers')
## plot the second graph on top of this
opar <- par(new = FALSE)
plot(histCucumber,xlim = xlim, ylim = ylim,
xaxt = 'n', yaxt = 'n', ## don't add axes
col = rgb(0,0,1,0.4), add = TRUE,
freq = FALSE) ## relative, not absolute frequency
## add a legend in the corner
legend('topleft',c('Carrots','Cucumbers'),
fill = rgb(1:0,0,0:1,0.4), bty = 'n',
border = NA)
par(opar)

唯一的问题是，如果直方图的断点是对齐的，它看起来会更好，这可能需要手动完成(在传递给hist的参数中)。

这里是类似于我只以r为基数给出的ggplot2的版本。我从@nullglob复制了一些。

生成数据

carrots <- rnorm(100000,5,2)
cukes <- rnorm(50000,7,2.5)

您不需要像使用ggplot2那样将其放入数据帧中。这种方法的缺点是你必须写出更多的情节细节。这样做的好处是你可以控制更多的情节细节。

## calculate the density - don't plot yet
densCarrot <- density(carrots)
densCuke <- density(cukes)
## calculate the range of the graph
xlim <- range(densCuke$x,densCarrot$x)
ylim <- range(0,densCuke$y, densCarrot$y)
#pick the colours
carrotCol <- rgb(1,0,0,0.2)
cukeCol <- rgb(0,0,1,0.2)
## plot the carrots and set up most of the plot parameters
plot(densCarrot, xlim = xlim, ylim = ylim, xlab = 'Lengths',
main = 'Distribution of carrots and cucumbers',
panel.first = grid())
#put our density plots in
polygon(densCarrot, density = -1, col = carrotCol)
polygon(densCuke, density = -1, col = cukeCol)
## add a legend in the corner
legend('topleft',c('Carrots','Cucumbers'),
fill = c(carrotCol, cukeCol), bty = 'n',
border = NA)

这是一个函数，我写了使用伪透明表示重叠的直方图

plotOverlappingHist <- function(a, b, colors=c("white","gray20","gray50"),
breaks=NULL, xlim=NULL, ylim=NULL){


ahist=NULL
bhist=NULL


if(!(is.null(breaks))){
ahist=hist(a,breaks=breaks,plot=F)
bhist=hist(b,breaks=breaks,plot=F)
} else {
ahist=hist(a,plot=F)
bhist=hist(b,plot=F)


dist = ahist$breaks[2]-ahist$breaks[1]
breaks = seq(min(ahist$breaks,bhist$breaks),max(ahist$breaks,bhist$breaks),dist)


ahist=hist(a,breaks=breaks,plot=F)
bhist=hist(b,breaks=breaks,plot=F)
}


if(is.null(xlim)){
xlim = c(min(ahist$breaks,bhist$breaks),max(ahist$breaks,bhist$breaks))
}


if(is.null(ylim)){
ylim = c(0,max(ahist$counts,bhist$counts))
}


overlap = ahist
for(i in 1:length(overlap$counts)){
if(ahist$counts[i] > 0 & bhist$counts[i] > 0){
overlap$counts[i] = min(ahist$counts[i],bhist$counts[i])
} else {
overlap$counts[i] = 0
}
}


plot(ahist, xlim=xlim, ylim=ylim, col=colors[1])
plot(bhist, xlim=xlim, ylim=ylim, col=colors[2], add=T)
plot(overlap, xlim=xlim, ylim=ylim, col=colors[3], add=T)
}

这是另一种方法是使用R对透明颜色的支持

a=rnorm(1000, 3, 1)
b=rnorm(1000, 6, 1)
hist(a, xlim=c(0,10), col="red")
hist(b, add=T, col=rgb(0, 1, 0, 0.5) )

下面是一个更简单的解决方案，使用基本图形和alpha混合(并不适用于所有图形设备):

set.seed(42)
p1 <- hist(rnorm(500,4))                     # centered at 4
p2 <- hist(rnorm(500,6))                     # centered at 6
plot( p1, col=rgb(0,0,1,1/4), xlim=c(0,10))  # first histogram
plot( p2, col=rgb(1,0,0,1/4), xlim=c(0,10), add=T)  # second

关键是颜色是半透明的。

编辑，两年多后:因为这刚刚得到了一个赞，我想我也可以添加一个代码产生的视觉效果，因为alpha混合是如此的有用:

Plotly的R API可能对你有用。下图是在这里。

library(plotly)
#add username and key
p <- plotly(username="Username", key="API_KEY")
#generate data
x0 = rnorm(500)
x1 = rnorm(500)+1
#arrange your graph
data0 = list(x=x0,
name = "Carrots",
type='histogramx',
opacity = 0.8)


data1 = list(x=x1,
name = "Cukes",
type='histogramx',
opacity = 0.8)
#specify type as 'overlay'
layout <- list(barmode='overlay',
plot_bgcolor = 'rgba(249,249,251,.85)')
#format response, and use 'browseURL' to open graph tab in your browser.
response = p$plotly(data0, data1, kwargs=list(layout=layout))


url = response$url
filename = response$filename


browseURL(response$url)

坦白说，我是队里的。

基本想法很好，但代码可以改进。[需要很长时间解释，因此需要单独回答，而不是评论。]

默认情况下，hist()函数绘制图形，因此您需要添加plot=FALSE选项。此外，通过plot(0,0,type="n",...)调用更清楚地建立绘图区域，您可以在其中添加轴标签，绘图标题等。最后，我想提一下，还可以使用阴影来区分两个直方图。代码如下:

set.seed(42)
p1 <- hist(rnorm(500,4),plot=FALSE)
p2 <- hist(rnorm(500,6),plot=FALSE)
plot(0,0,type="n",xlim=c(0,10),ylim=c(0,100),xlab="x",ylab="freq",main="Two histograms")
plot(p1,col="green",density=10,angle=135,add=TRUE)
plot(p2,col="blue",density=10,angle=45,add=TRUE)

这里是结果(有点太宽，因为RStudio:-)):

set.seed(42)
hist(rnorm(500,4),xlim=c(0,10),col='skyblue',border=F)
hist(rnorm(500,6),add=T,col=scales::alpha('red',.5),border=F)

结果是……

更新:这个重叠函数可能对某些人也有用。

hist0 <- function(...,col='skyblue',border=T) hist(...,col=col,border=border)

我觉得hist0的结果比hist看起来更漂亮

hist2 <- function(var1, var2,name1='',name2='',
breaks = min(max(length(var1), length(var2)),20),
main0 = "", alpha0 = 0.5,grey=0,border=F,...) {


library(scales)
colh <- c(rgb(0, 1, 0, alpha0), rgb(1, 0, 0, alpha0))
if(grey) colh <- c(alpha(grey(0.1,alpha0)), alpha(grey(0.9,alpha0)))


max0 = max(var1, var2)
min0 = min(var1, var2)


den1_max <- hist(var1, breaks = breaks, plot = F)$density %>% max
den2_max <- hist(var2, breaks = breaks, plot = F)$density %>% max
den_max <- max(den2_max, den1_max)*1.2
var1 %>% hist0(xlim = c(min0 , max0) , breaks = breaks,
freq = F, col = colh[1], ylim = c(0, den_max), main = main0,border=border,...)
var2 %>% hist0(xlim = c(min0 , max0),  breaks = breaks,
freq = F, col = colh[2], ylim = c(0, den_max), add = T,border=border,...)
legend(min0,den_max, legend = c(
ifelse(nchar(name1)==0,substitute(var1) %>% deparse,name1),
ifelse(nchar(name2)==0,substitute(var2) %>% deparse,name2),
"Overlap"), fill = c('white','white', colh[1]), bty = "n", cex=1,ncol=3)


legend(min0,den_max, legend = c(
ifelse(nchar(name1)==0,substitute(var1) %>% deparse,name1),
ifelse(nchar(name2)==0,substitute(var2) %>% deparse,name2),
"Overlap"), fill = c(colh, colh[2]), bty = "n", cex=1,ncol=3) }

的结果

par(mar=c(3, 4, 3, 2) + 0.1)
set.seed(100)
hist2(rnorm(10000,2),rnorm(10000,3),breaks = 50)

是

这么多伟大的答案，但由于我刚刚写了一个函数(plotMultipleHistograms()在“basicPlotteR”包)函数来做到这一点，我想我应该添加另一个答案。

这个函数的优点是，它自动设置适当的X轴和Y轴限制，并定义在所有分布中使用的公共容器集。

下面是如何使用它:

# Install the plotteR package
install.packages("devtools")
devtools::install_github("JosephCrispell/basicPlotteR")
library(basicPlotteR)


# Set the seed
set.seed(254534)


# Create random samples from a normal distribution
distributions <- list(rnorm(500, mean=5, sd=0.5),
rnorm(500, mean=8, sd=5),
rnorm(500, mean=20, sd=2))


# Plot overlapping histograms
plotMultipleHistograms(distributions, nBins=20,
colours=c(rgb(1,0,0, 0.5), rgb(0,0,1, 0.5), rgb(0,1,0, 0.5)),
las=1, main="Samples from normal distribution", xlab="Value")

plotMultipleHistograms()函数可以接受任意数量的分布，并且所有一般的绘图参数都应该与它一起工作(例如:las， main等)。