多变量图的 geom_segment 线垂直

问题描述

下面的绘图代码使所有颜色的线段线会聚在离散 x 变量的中心。怎样才能使线段线对于每个颜色的 x 变量都是垂直的？

#~ Plot data
ggplot(data = data0,aes(x = v3,y = v4)) +
  geom_point(aes(colour = v2),size = 2,alpha = .25,position = position_jitterdodge(jitter.width = 0.15,seed = 1)
  ) +
  stat_summary(fun = mean,geom = "point",size = 5,aes(colour = v2),position = position_dodge(0.75)) +
  geom_segment(data = data1,xend = v3,y = v4,yend = grand_mean,colour = v2),size = 1,position = position_dodge(width = 0.75)) +
  geom_hline(data = data1,aes(yintercept = grand_mean)) +
  facet_wrap(facets = vars(v1)) +
  theme_bw()

数据：

#~ Raw data
data0 <- data.frame(v1 = sample(c("foo","bar"),1000,replace = TRUE),v2 = sample(letters[1:4],v3 = sample(1:4,v4 = rnorm(1000))

#~ Summary data
data1 <- data0 %>%
  group_by(v1,v2,v3) %>%
  summarise(v4 = mean(v4))
data1$grand_mean <- mean(data0$v4)

解决方法

position_dodge() 无法处理 xend 和 yend。改用 geom_line() 或 geom_linerange()：

ggplot(data = data0,aes(x = v3,y = v4)) +
  geom_point(aes(colour = v2),size = 2,alpha = .25,position = position_jitterdodge(jitter.width = 0.15,seed = 1)
  ) +
  stat_summary(fun = mean,geom = "point",size = 5,aes(colour = v2),position = position_dodge(0.75)) +
  geom_linerange(data = data1,ymin = v4,ymax = grand_mean,colour = v2),size = 1,position = position_dodge(width = 0.75)) +
  geom_hline(data = data1,aes(yintercept = grand_mean)) +
  facet_wrap(facets = vars(v1)) +
  theme_bw()

更长的答案 - 我手动计算每个组的 v3_revised（x 轴）位置。

library(dplyr)
library(ggplot2)

#~ Raw data
data0 <- data.frame(v1 = sample(c("foo","bar"),1000,replace = TRUE),v2 = sample(letters[1:4],v3 = sample(1:4,v4 = rnorm(1000))

v2_unique <- sort(unique(data0$v2))
x_variation <- seq(from = -0.3,to = 0.3,length.out = length(v2_unique))
names(x_variation) <- v2_unique
#~ Summary data
data0 <- data0 %>%
  mutate(v3_revised = v3 + x_variation[v2])
data1 <- data0 %>%
  group_by(v1,v2,v3_revised) %>%
  summarise(v4 = mean(v4))
#> `summarise()` has grouped output by 'v1','v2'. You can override using the `.groups` argument.
data1$grand_mean <- mean(data0$v4)

#~ Plot data
ggplot(data = data0,aes(x = v3_revised,seed = 1)) +
  stat_summary(fun = mean,aes(colour = v2)) +
  geom_segment(data = data1,xend = v3_revised,y = v4,yend = grand_mean,size = 1) +
  geom_hline(data = data1,aes(yintercept = grand_mean)) +
  facet_wrap(facets = vars(v1)) +
  theme_bw()
#> Warning: position_jitterdodge requires non-overlapping x intervals

#> Warning: position_jitterdodge requires non-overlapping x intervals

^{由 reprex package (v2.0.0) 于 2021 年 6 月 7 日创建}

geom-segment ggplot2 r r