r - 从分类变量创建直方图(不是条形图)

Question

我知道您通常应该对分类变量使用条形图，但在我的情况下，有人将连续变量分成几组，无论如何有一个直方图会很好。

这是我想要得到的(除了直方图):

par(oma=c(2,0,0,0))  #so labels are not cut off  
barplot(table(hhincome),ylab = "Frequency", main = "Netto houshold income",
          border="black", col="grey",las=2)

(注意:直方图在条形图和 x 轴之间没有空格)

数据:

hhincome <- structure(c(4L, 4L, 1L, 6L, 8L, 1L, 4L, 5L, 2L, 3L, 1L, 5L, 1L, 7L, 6L, 7L, 3L, 2L, 6L, 7L, 8L, 4L, 7L, 8L, 7L, 4L, 5L, 5L, 5L, 9L, 7L, 5L, 8L, 8L, 6L, 5L, 5L, 3L, 5L, 4L, 3L, 5L, 3L, 5L, 4L, 4L, 5L, 7L, 6L, 7L, 2L, 6L, 1L, 7L, 4L, 4L, 5L, 2L, 4L, 6L, 6L, 8L, 6L, 7L, 4L, 7L, 9L, 1L, 4L, 6L, 2L, 6L, 8L, 6L, 5L, 8L, 7L, 9L, 7L, 9L, 8L, 5L, 5L, 7L, 6L, 2L, 7L, 6L, 6L, 1L, 7L, 7L, 2L, 6L, 6L, 6L, 7L, 5L, 2L, 2L, 9L, 6L, 7L, 7L, 5L, 6L, 6L, 5L, 5L, 7L, 8L, 6L, 6L, 3L, 7L, 6L, 4L, 5L, 5L, 4L, 8L, 3L, 4L, 6L, 5L, 7L, 3L, 4L, 7L, 5L, 3L, 6L, 2L, 2L, 5L, 2L, 4L, 8L, 4L, 3L, 2L, 7L, 2L, 5L, 2L, 1L, 8L, 7L, 3L, 6L, 6L, 7L, 2L, 9L, 3L, 3L, 5L, 7L, 7L, 5L, 6L, 8L, 5L, 6L, 5L, 5L, 7L, 6L, 5L, 5L, 6L, 10L, 3L, 6L, 6L, 3L, 2L, 4L, 9L, 2L, 6L, 7L, 1L, 5L, 6L, 5L, 4L, 7L, 5L, 2L, 6L, 3L, 3L, 2L, 7L, 6L, 6L, 5L, 7L, 6L, 1L, 7L, 3L, 2L, 5L, 5L, 3L, 3L, 3L, 4L, 1L, 7L, 5L, 3L, 3L, 3L, 8L, 6L, 3L, 2L, 5L, 5L, 4L, 1L, 4L, 1L, 2L, 6L, 4L, 5L, 5L, 8L, 3L, 7L, 7L, 3L, 4L, 4L, 4L, 3L, 4L, 6L, 3L, 3L, 4L, 7L, 2L, 6L, 8L, 5L, 3L, 3L, 6L, 2L, 3L, 4L, 3L, 5L, 5L, 7L, 8L, 6L, 6L, 8L, 4L, 7L, 9L, 1L, 5L, 3L, 2L, 3L, 6L, 3L, 4L, 6L, 3L, 7L, 3L, 1L, 6L, 8L, 4L, 4L, 5L, 6L, 8L, 4L, 4L, 2L, 8L, 6L, 5L, 1L, 4L, 6L, 3L, 5L, 6L, 6L, 4L, 4L, 7L, 8L, 3L, 3L, 4L, 6L, 1L, 6L, 7L, 7L, 1L, 3L, 5L, 6L, 7L, 2L, 3L, 6L, 3L, 2L, 7L, 9L, 3L, 10L, 6L, 9L, 3L, 5L, 11L, 10L, 7L, 8L, 8L, 5L, 5L, 3L, 5L, 8L, 9L, 3L, 2L, 6L, 7L, 5L, 5L, 7L, 5L, 8L, 7L, 11L, 7L, 3L, 3L, 5L, 6L, 8L, 2L, 5L, 6L, 6L, 9L, 4L, 5L, 6L, 7L, 6L, 3L, 8L, 7L, 6L, 9L, 7L, 7L, 4L, 7L, 9L, 3L, 9L, 6L, 11L, 6L, 9L, 4L, 7L, 2L, 7L, 8L, 6L, 8L, 6L, 6L, 6L, 5L, 5L, 2L, 4L, 9L, 7L, 6L, 9L, 5L, 3L, 8L, 2L, 5L, 4L, 7L, 4L, 8L, 6L, 1L, 6L, 5L, 9L, 6L, 7L, 1L, 1L, 4L, 3L, 11L, 3L, 6L, 5L, 2L, 7L, 5L, 6L, 8L, 8L, 3L, 4L, 9L, 6L, 5L, 7L, 8L, 8L, 6L, 8L, 1L, 3L, 5L, 8L, 1L, 6L, 7L, 9L, 8L, 4L, 4L, 6L, 5L, 7L, 6L, 7L, 7L, 3L, 9L, 5L, 8L, 11L, 3L, 7L, 6L, 7L, 8L, 8L, 2L, 2L, 3L, 2L, 5L, 6L, 5L, 7L, 4L, 7L, 2L, 7L, 2L, 2L, 4L, 7L, 6L, 9L, 8L, 5L, 1L, 6L, 3L, 10L, 1L, 7L, 4L, 7L, 5L, 6L, 8L, 4L, 8L, 4L, 5L, 8L, 6L, 7L, 7L, 8L, 7L, 7L, 6L, 7L, 5L, 7L, 9L, 5L, 7L, 4L, 2L, 7L, 3L, 6L, 3L, 8L, 5L, 2L, 6L, 7L, 7L), .Label = c("Less than 500 €", "500-900 €", "900-1300 €", "1300-1500 €", "1500-2000 €", "2000-2600 €", "2600-3500 €", "3500-4500 €", "4500-6000 €", "6000-8000 €", "8000€ or more"), class = "factor")

Answer 1

感谢 Zheyuan Li 我已经有了答案。我可以简单地创建一个看起来非常像直方图的条形图，而不是强制使用直方图:

par(oma=c(2,0,0,0))   #so labels are not cut off   
barplot(table(hhincome2), space = 0, # set space between bars to zero
              ylab = "Frequency", main = "Netto houshold income",
              border="black", col="grey",las=2) 
axis(1, at =  hhincome,labels = FALSE) # at x-axis at category borders
box()

编辑:我刚刚找到了另一种方法:

h <- hist(as.numeric(hhincome2) #as.numeric converst factor levels to numeric values
          , xlab = "", ylab = "Frequency", main = "Netto houshold income \n(with normal disttribution curve)",
             border="black", col="grey",las=2, 
          xaxt='n') #this supresses the x-axis which would disply levels instead values
axis(1, at =  hhincome2, labels = hhincome2, las=2) #just add factor level labels as labels
box()

这样也可以添加正态分布曲线:

xfit<-seq(min(as.numeric(hhincome2)),max(as.numeric(hhincome2)),length=1100) 
yfit<-dnorm(xfit,mean=mean(as.numeric(hhincome2)),sd=sd(as.numeric(hhincome2))) 
yfit <- yfit*diff(h$mids[1:2])*length(as.numeric(hhincome2)) 
lines(xfit, yfit, col="black", lwd=2)