使用@Ramnath在this上一个问题中的答案中得到的一些代码,我想找到x的值,它将平均分配两条曲线之间的重叠区域。请参阅以下示例:
library(ggplot2)
x = seq(-7, 10, length = 200)
y1 = dnorm(x, mean = 0,sd = 1)
y2 = dnorm(x, mean = 3,sd = 2)
mydf = data.frame(x, y1, y2)
p0 = ggplot(mydf, aes(x = x)) +
geom_line(aes(y = y1), colour = 'blue') +
geom_line(aes(y = y2), colour = 'red') +
geom_area(aes(y = pmin(y1, y2)), fill = 'gray60')
任何建议将不胜感激!
在下面的方法中,我们找到累积的重叠区域,然后找到该累积区域是总重叠区域的一半的x值。
为了说明,我添加了额外的数据列来标记所有步骤,但如果您只是想直接找到分界线的位置,则不需要这样做。
# overlap
mydf$overlap = apply(mydf[,c("y1","y2")], 1, min)
# area of overlap
mydf$overlap.area = cumsum(mydf$overlap * median(diff(mydf$x)))
# Find x that divides overlap area in half
# Method 1: Directly from the data. Could be inaccurate if x values are
# not sufficiently close together.
x0a = mydf$x[which.min(abs(mydf$overlap.area - 0.5*max(mydf$overlap.area)))]
# Method 2: Use uniroot function to find x value where cumulative overlap
# area is 50% of total overlap area. More accurate.
# First generate an interpolation function for cumulative area.
# Subtract half the cumulative area so that function will cross
# zero at the halfway point
f = approxfun(mydf$x, mydf$overlap.area - 0.5*max(mydf$overlap.area))
# Find x value at which interpolation function crosses zero
x0b = uniroot(f, range(mydf$x))$root
p0 = ggplot(mydf, aes(x = x)) +
geom_line(aes(y = y1), colour = 'blue') +
geom_line(aes(y = y2), colour = 'red') +
geom_area(aes(y = pmin(y1, y2)), fill = 'gray60') +
geom_line(aes(y=overlap), colour="purple") +
geom_line(aes(y=overlap.area), colour="green") +
geom_vline(xintercept=c(x0a,x0b), color=c("orange","darkgreen"),
linetype=c("solid", "dashed")) +
theme_classic()
p0