R语言sankeyNetwork桑基图颜色匹配错误及可视化方案问询

颜色匹配错误是两个原因导致的：

• 提前对dummynodes的name列做了gsub("_old","")处理，导致节点表出现重复名称，D3的序数比例尺无法正确映射重复键值
• sankeyNetwork的colourScale默认匹配节点表的name列值，重复值会导致后续映射覆盖前序规则

不需要修改现有数据结构，只需要新增节点分组列，把颜色映射到分组而非显示名称即可，修改后完整代码如下：

library(networkD3)
library(dplyr)

stat.old<-c("new2021","casual_old","established_local_old","established_old","unknown_old","questionable_old")
stat.new<-c("casual","established_local","established","unknown","questionable", "extinct")

dummytest<-expand.grid(stat.old=stat.old,stat.new=stat.new)
# value定义对应“流”中的物种数量
dummytest$value<-sample(c(0:50),36,replace=T)

# 构造节点表时保留原始唯一名称，新增group列存储显示用的分类名
dummynodes<-data.frame(name = unique(c(as.character(dummytest$stat.old), as.character(dummytest$stat.new)))) %>%
  mutate(group = gsub("_old","", name))

# 使用match()函数获取节点ID
dummytest$idsource<-match(dummytest$stat.old, dummynodes$name)-1
dummytest$idtarget<-match(dummytest$stat.new, dummynodes$name)-1

# 颜色映射直接对应group的唯一值即可
my_color <- 'd3.scaleOrdinal() 
.domain(["new2021","casual","established_local","established","unknown","questionable", "extinct"]) 
.range(["red","darkolivegreen2","darkolivegreen3","darkolivegreen4","gold3","darkgrey", "black"])'

# 新增nodeGroup参数指定映射分组列
sankeyNetwork(Links=dummytest, Nodes=dummynodes, 
              Source="idsource",Target="idtarget", Value="value", 
              NodeID="group", sinksRight=F, fontSize=22, 
              fontFamily="Calibri", colourScale=my_color,
              nodeGroup = "group")

如果更习惯ggplot2语法，可以用ggalluvial包实现同类可视化，颜色映射逻辑更简单，不需要处理D3语法：

library(ggplot2)
library(ggalluvial)

# 直接用原始流转数据绘图
ggplot(dummytest,
       aes(y = value, axis1 = stat.old, axis2 = stat.new)) +
  geom_alluvium(width = 1/12, alpha = 0.6) +
  geom_stratum(aes(fill = gsub("_old","", after_stat(stratum))), width = 1/12) +
  scale_x_discrete(limits = c("旧分类状态", "新分类状态"), expand = c(0.05, 0.05)) +
  scale_fill_manual(values = c("new2021" = "red",
                               "casual" = "darkolivegreen2",
                               "established_local" = "darkolivegreen3",
                               "established" = "darkolivegreen4",
                               "unknown" = "gold3",
                               "questionable" = "darkgrey",
                               "extinct" = "black")) +
  labs(y = "物种数量") +
  theme_minimal() +
  theme(legend.position = "none")

内容的提问来源于stack exchange，提问作者Gmichael