如何在节点处加入 ggalluvial 中的数据流

Question

我有两个数据集，显示了 3 个不同时间段内各地区之间的人员流动，其中中间时间段 (t2) 是各个时间段之间的唯一链接。现在我想使用 ggplot2 在 r 中绘制冲积图。下面的代码可以工作，但会产生一个丑陋的图，因为流量没有正确地来自节点（由于缺乏更好的单词）。理想情况下，可以这么说，流量将从节点进入的同一级别开始。我如何重新格式化数据才能实现这一点？在当前示例中，“D”是所需大小的两倍。

library(dplyr)
library(ggalluvial)
library(tidyr)

data_1 <- tibble(t1 = c("A", "B", "B","C"),  
                 t2 = c("D", "E", "F", "G"),
                 value = c(99, 50, 50, 100))


data_2 <- tibble(t2 = c("D", "E", "F", "G"),  
                 t3 = c("H", "H", "I", "J"),
                 value = c(100, 100, 80, 100))


data_1_long <-  data_1 %>%
  mutate(flow = 1:n()) %>%
  pivot_longer(-c(flow, value), names_to = "time", values_to = "district")

data_2_long <-  data_2 %>%
  mutate(flow = (max(data_1_long$flow)+1):(max(data_1_long$flow)+nrow(data_2))) %>%
  pivot_longer(-c(flow, value), names_to = "time", values_to = "district")

data_long <- bind_rows(data_1_long,
                       data_2_long)



plot_alluvial <-ggplot(data = data_long ,
                       aes(x = time,
                           stratum = district,
                           alluvium = flow,
                           y = value , 
                           label = district))  +
  geom_flow(stat = "alluvium", lode.guidance = "backfront",
            color = "darkgray") +
  geom_stratum()  +
  geom_text(stat = "stratum") +
  theme(legend.position = "bottom") 
plot_alluvial

Answer 1

我认为问题在于您的数据并不真正适合冲积图，它显示了“固定”数量的实体如何切换类别。进入某个类别和离开该类别的人数是可变的。换句话说，t2 输入的大小与输出的大小不同。例如，“E”有 50 个进去，但有 100 个出去。 在这种情况下，使用加权方向图可能会更好：

library(igraph)
library(tidygraph)
library(ggraph)

data_1 <- tibble(t1 = c("A", "B", "B","C"),  
                 t2 = c("D", "E", "F", "G"),
                 value = c(99, 50, 50, 100))


data_2 <- tibble(t2 = c("D", "E", "F", "G"),  
                 t3 = c("H", "H", "I", "J"),
                 value = c(100, 100, 80, 100))

cbind(setNames(data_1, c('from', 'to', 'weight')), time = 't1-t2') |>
  rbind(cbind(setNames(data_2, c('from', 'to', 'weight')), time = 't2-t3')) |>
  igraph::graph.data.frame() |>
  as_tbl_graph() |>
  mutate(y = c(1:3, seq(0.5, 3.5, 1), 1:3), 
         x = c(0, 0, 0, 2, 2, 2, 2, 4, 4, 4)) |>
  ggraph(layout = 'manual', x = x, y = y) +
  geom_edge_diagonal(aes(width = weight/10), alpha = 0.2, flipped = TRUE) +
  geom_node_circle(aes(r = 0.2), fill = 'white') +
  geom_node_circle(aes(r = 0.2, fill = name), alpha = 0.5) +
  geom_node_text(aes(label = name), size = 6) +
  scale_edge_width_identity() +
  annotate('text', x = c(0, 2, 4), y = 4, label = c('t1', 't2', 't3'), 
           size = 6) +
  coord_equal() +
  theme_void() +
  theme(legend.position = 'none')