r - 由线条连接的条形图/如何连接在 R/ggplot2 中使用 grid.arrange 排列的两个图形

Question

在 Facebook 研究中，我发现了这些漂亮的条形图，这些条形图由线条连接以指示排名变化:


https://research.fb.com/do-jobs-run-in-families/

我想使用 ggplot2 创建它们。条形图部分很简单:

library(ggplot2)
library(ggpubr)
state1 <- data.frame(state=c(rep("ALABAMA",3), rep("CALIFORNIA",3)), 
                 value=c(61,94,27,10,30,77), 
                 type=rep(c("state","local","fed"),2),
                 cumSum=c(rep(182,3), rep(117,3)))
state2 <- data.frame(state=c(rep("ALABAMA",3), rep("CALIFORNIA",3)), 
                 value=c(10,30,7,61,94,27), 
                 type=rep(c("state","local","fed"),2),
                 cumSum=c(rep(117,3), rep(182,3)))
fill <- c("#40b8d0", "#b2d183", "#F9756D")

p1 <- ggplot(data = state1) +
  geom_bar(aes(x = reorder(state, value), y = value, fill = type), stat="identity") +
  theme_bw() + 
  scale_fill_manual(values=fill) + 
  labs(x="", y="Total budget in 1M$") +
  theme(legend.position="none", 
        legend.direction="horizontal", 
        legend.title = element_blank(),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.border = element_blank(), panel.background = element_blank()) +
  coord_flip() 

p2 <- ggplot(data = state2) +
  geom_bar(aes(x = reorder(state, value), y = value, fill = type), stat="identity") +
  theme_bw() + 
  scale_fill_manual(values=fill) + labs(x="", y="Total budget in 1M$") +
  theme(legend.position="none", 
        legend.direction="horizontal", 
        legend.title = element_blank(),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.border = element_blank(), 
        panel.background = element_blank()) +
  scale_x_discrete(position = "top") + 
  scale_y_reverse() +
  coord_flip()

p3 <- ggarrange(p1, p2, common.legend = TRUE, legend = "bottom")

但我无法想出解决线路部分的方法。添加行时，例如到左边

p3 + geom_segment(aes(x = rep(1:2, each=3), xend = rep(1:10, each=3), 
                   y = cumSum[order(cumSum)], yend=cumSum[order(cumSum)]+10), size = 1.2)

问题是这些线将无法跨越到右侧。
它看起来像这样:


基本上，我想将左侧的“加利福尼亚”栏与右侧的凯福尼亚栏连接起来。

为此，我认为，我必须以某种方式访问​​图表的上级。我查看了视口(viewport)，并能够用由 geom_segment 制成的图表覆盖两个条形图，但后来我无法找出线条的正确布局:

subplot <- ggplot(data = state1) + 
  geom_segment(aes(x = rep(1:2, each=3), xend = rep(1:2, each=3), 
                   y = cumSum[order(cumSum)], yend =cumSum[order(cumSum)]+10), 
               size = 1.2)

vp <- viewport(width = 1, height = 1, x = 1, y = unit(0.7, "lines"), 
               just ="right", "bottom"))
print(p3)
print(subplot, vp = vp)

非常感谢帮助或指针。

Answer 1

这是一个纯 ggplot2 解决方案，它将底层数据帧组合成一个并将所有内容绘制在一个图中:

数据操作:

library(dplyr)    
bar.width <- 0.9

# combine the two data sources
df <- rbind(state1 %>% mutate(source = "state1"),
            state2 %>% mutate(source = "state2")) %>%

  # calculate each state's rank within each data source
  group_by(source, state) %>%
  mutate(state.sum = sum(value)) %>%
  ungroup() %>%
  group_by(source) %>%
  mutate(source.rank = as.integer(factor(state.sum))) %>%
  ungroup() %>%

  # calculate the dimensions for each bar
  group_by(source, state) %>%
  arrange(type) %>% 
  mutate(xmin = lag(cumsum(value), default = 0),
         xmax = cumsum(value),
         ymin = source.rank - bar.width / 2,
         ymax = source.rank + bar.width / 2) %>% 
  ungroup() %>%

  # shift each data source's coordinates away from point of origin,
  # in order to create space for plotting lines
  mutate(x = ifelse(source == "state1", -max(xmax) / 2, max(xmax) / 2)) %>%
  mutate(xmin = ifelse(source == "state1", x - xmin, x + xmin),
         xmax = ifelse(source == "state1", x - xmax, x + xmax)) %>%

  # calculate label position for each data source
  group_by(source) %>%
  mutate(label.x = max(abs(xmax))) %>%
  ungroup() %>%
  mutate(label.x = ifelse(source == "state1", -label.x, label.x),
         hjust = ifelse(source == "state1", 1.1, -0.1))

阴谋:

ggplot(df, 
       aes(x = x, y = source.rank,
           xmin = xmin, xmax = xmax, 
           ymin = ymin, ymax = ymax,
           fill = type)) +
  geom_rect() +
  geom_line(aes(group = state)) +
  geom_text(aes(x = label.x, label = state, hjust = hjust),
            check_overlap = TRUE) +

  # allow some space for the labels; this may be changed
  # depending on plot dimensions
  scale_x_continuous(expand = c(0.2, 0)) +
  scale_fill_manual(values = fill) +

  theme_void() +
  theme(legend.position = "top")

数据源(与@camille 相同):

set.seed(1017)

state1 <- data_frame(
  state = rep(state.name[1:5], each = 3),
  value = floor(runif(15, 1, 100)),
  type = rep(c("state", "local", "fed"), times = 5)
)

state2 <- data_frame(
  state = rep(state.name[1:5], each = 3),
  value = floor(runif(15, 1, 100)),
  type = rep(c("state", "local", "fed"), times = 5)
)