将因子绘制为线或区域而不是矩形

Question

我有一个因子和一个数值向量。当我绘制这些使用

plot(factor ~ vector, data)

看起来像这样：

但我希望它看起来像这样：

y 轴代表（累积）频率。

问题是，当我告诉 R 使用线条绘图时，R 告诉我

In rect(xleft, ybottom, xright, ytop, col = col, ...) :
  graphical parameter "type" is obsolete

那么我该怎么做呢？

使用基础 plot() 而不是 ggplot 或类似的解决方案的额外分数。颜色不是必需的，可以是灰度值。

---

样本数据：

a.factor <- c("level1", "level1", "level1", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level3", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level2", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level1", "level1", "level1", "level2", "level1", "level1", "level2", "level1", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level1", "level2", "level1", "level1", "level1", "level1", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level2", "level2", "level2", "level2", "level1", "level1", "level2", "level1", "level2", "level2", "level2", "level2", "level2", "level1", "level2", "level2", "level1", "level2", "level2", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level2", "level1", "level2", "level2", "level2", "level1", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level2", "level2", "level2", "level2", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level3", "level1", "level1", "level1", "level3", "level2", "level1", "level2", "level2", "level1", "level1", "level2", "level2", "level2", "level2", "level2", "level2", "level1", "level1", "level1", "level1", "level1", "level1", "level2", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level2", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level1", "level2", "level2", "level2", "level1", "level2", "level2", "level2", "level2", "level1", "level2", "level2", "level1", "level1")
b.vector <- c(314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 314, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 315, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 316, 317, 317, 317, 317, 317, 317, 317, 317, 317, 317, 317, 318, 318, 318, 318, 318, 318, 318, 319, 319, 319, 319, 319, 320, 320, 320, 320, 320, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321, 321)
dat <- data.frame(a.factor, b.vector)
plot(a.factor ~ b.vector, dat)

Answer 1

这是一个使用 ggplot 和 geom_area 的解决方案。为了正确强制堆叠数据中不存在的组合，需要进行一些聚合。

library(ggplot2)
library(data.table)
setDT(dat)

dat_agg <-as.data.table(table(dat)) #thanks @Maju116; sometimes I do things too complicated.


#plot
p1 <- ggplot(dat_agg, 
             aes(x = b.vector, y = N,group = a.factor)) +
  geom_area(aes(fill = a.factor), position = "stack")
p1

编辑：仅使用 base-R（不错的挑战）

dat <- data.frame(a.factor, b.vector)

需要将数据转换为一系列 x 和 y 坐标来绘制多边形。它们需要按正确的顺序排列（在本例中，x 增加的“下”范围和 x 减小的“上限”范围）。

#calculate 'upper range' of each polygon
#using cumsum as they're stacked
max_points <- apply(table(dat),MARGIN=2,cumsum)

#lower range for first level is 0, for other levels 
#lower range is upper range of level below it.
min_points <- rbind(0, max_points[1:2,ncol(max_points):1]) #reverse order
rownames(min_points) <- rownames(max_points)

#combine
polydata <- cbind(max_points,min_points)

#x position
x_vector <- as.numeric(colnames(polydata))

#colors
mycols <- c("red","blue","green")

#plotting (empty plot first, then add polygons)
plot(x=b.vector, y=seq(0,100,length.out=length(b.vector)),type="n",
     ylab="frequency")
lapply(1:nrow(polydata),function(i){
  polygon(x=x_vector, y=as.numeric(polydata[i,]),col=mycols[i])
})
legend(x=320, y=100, legend=rownames(polydata),fill=mycols)

Answer 2

你想要这样的东西吗？

dane<-data.frame(a.factor,b.vector)
dane<-as.data.frame(table(dane))
library(ggplot2)
ggplot(dane,aes(group=a.factor,x=b.vector,y=Freq,color=a.factor))+geom_point()+geom_line()