求助：用ggplot绘制混合变量堆叠条形图（多调色板+分类图例）

我希望使用ggplot绘制堆叠条形图，横轴为变量，这些变量的响应类型不同：部分为Y/N二分类、部分为Old/Young二分类、还有部分为0-5的Likert量表。需为不同类型的变量分配不同的调色板，并添加能体现不同调色板/变量类型的图例。附上示例数据代码，恳请协助实现。

X1<-c("N","N","N","N","Y","N","Y","N","N","N","N","N","Y","N","N","Y","N","N","N","Y","N","Y","Y","N","N","Y","Y","Y","N","N","N","N","N","N","N","N","Y","N","Y","N","N","N","N","Y","N","N","Y","N","Y","Y","N","Y","N","N")
X2 <-c("N","N","N","N","Y","N","Y","N","N","N","N","N","Y","N","N","Y","N","N","N","Y","N","Y","Y","N","N","Y","Y","Y","N","N","N","N","N","N","N","N","Y","N","Y","N","N","N","N","Y","N","N","Y","N","Y","Y","N","Y","N","N")
X3<-c(1,1,0,1,2,0,0,0,0,0,1,1,1,2,0,1,2,1,1,0,0,0,4,1,0,0,0,0,1,0,2,0,0,2,1,1,0,0,0,1,1,0,1,0,1,0,1,1,0,1,0,1,1,1)
X4 <-c("YouNg","Old","Old","YouNg","Old","Old","Old","YouNg","YouNg","YouNg","Old","Old","Old",
       "Old","Old","Old","Old","YouNg","Old","Old","Old","YouNg","YouNg","Old","Old","Old",
       "Old","Old","Old","Old","Old","Old","Old","YouNg","Old","YouNg","Old","YouNg","Old",
       "Old","YouNg","Old","YouNg","YouNg","Old","Old","Old","YouNg","Old","Old","Old","YouNg", "Old", "Old")

Y <- data.frame(X1, X2, X3, X4)

核心思路 #

• 将宽格式数据转换为长格式，适配ggplot的绘图逻辑
• 为每个变量标记类型，便于区分调色板
• 为不同类型变量自定义专属调色板，避免颜色混淆
• 通过图例分组和辅助标注，清晰展示变量类型与对应颜色的关系

完整代码实现 #

# 加载依赖包
library(ggplot2)
library(dplyr)
library(tidyr)
library(stringr)

# 用户提供的示例数据
X1<-c("N","N","N","N","Y","N","Y","N","N","N","N","N","Y","N","N","Y","N","N","N","Y","N","Y","Y","N","N","Y","Y","Y","N","N","N","N","N","N","N","N","Y","N","Y","N","N","N","N","Y","N","N","Y","N","Y","Y","N","Y","N","N")
X2 <-c("N","N","N","N","Y","N","Y","N","N","N","N","N","Y","N","N","Y","N","N","N","Y","N","Y","Y","N","N","Y","Y","Y","N","N","N","N","N","N","N","N","Y","N","Y","N","N","N","N","Y","N","N","Y","N","Y","Y","N","Y","N","N")
X3<-c(1,1,0,1,2,0,0,0,0,0,1,1,1,2,0,1,2,1,1,0,0,0,4,1,0,0,0,0,1,0,2,0,0,2,1,1,0,0,0,1,1,0,1,0,1,0,1,1,0,1,0,1,1,1)
X4 <-c("YouNg","Old","Old","YouNg","Old","Old","Old","YouNg","YouNg","YouNg","Old","Old","Old",
       "Old","Old","Old","Old","YouNg","Old","Old","Old","YouNg","YouNg","Old","Old","Old",
       "Old","Old","Old","Old","Old","Old","Old","YouNg","Old","YouNg","Old","YouNg","Old",
       "Old","YouNg","Old","YouNg","YouNg","Old","Old","Old","YouNg","Old","Old","Old","YouNg", "Old", "Old")

Y <- data.frame(X1, X2, X3, X4)

# 1. 数据预处理：宽转长 + 标记变量类型 + 统一响应文本格式
Y_long <- Y %>%
  pivot_longer(cols = everything(), names_to = "variable", values_to = "response") %>%
  mutate(
    # 统一X4的大小写（YouNg转为Young）
    response = ifelse(variable == "X4", str_to_title(response), as.character(response)),
    # 标记变量所属类型
    var_type = case_when(
      variable %in% c("X1", "X2") ~ "Y/N 二分类",
      variable == "X4" ~ "Old/Young 二分类",
      variable == "X3" ~ "0-5 Likert量表"
    )
  ) %>%
  arrange(var_type, response) # 确保堆叠顺序一致

# 2. 自定义分类型调色板
palettes <- list(
  "Y/N 二分类" = c("N" = "#1f77b4", "Y" = "#ff7f0e"),
  "Old/Young 二分类" = c("Old" = "#2ca02c", "Young" = "#d62728"),
  "0-5 Likert量表" = c("0" = "#f8f9fa", "1" = "#e9ecef", "2" = "#dee2e6", "3" = "#ced4da", "4" = "#adb5bd", "5" = "#6c757d")
)
combined_palette <- unlist(palettes) # 合并为ggplot可用的向量

# 3. 绘制堆叠条形图
ggplot(Y_long, aes(x = variable, fill = interaction(response, var_type, sep = " - "))) +
  geom_bar(position = "fill") + # 绘制百分比堆叠图
  scale_fill_manual(
    values = combined_palette,
    name = "响应类别",
    labels = function(x) gsub("(.*) - (.*)", "\\1", x), # 拆分图例标签，只显示响应值
    guide = guide_legend(
      ncol = 1,
      keyheight = unit(0.8, "cm"),
      override.aes = list(size = 0.5)
    )
  ) +
  # 添加变量类型的顶部标注
  annotate("text", x = 1.5, y = 1.05, label = "Y/N 二分类", size = 4, fontface = "bold") +
  annotate("text", x = 3, y = 1.05, label = "Old/Young 二分类", size = 4, fontface = "bold") +
  annotate("text", x = 4, y = 1.05, label = "0-5 Likert量表", size = 4, fontface = "bold") +
  # 调整坐标轴与主题
  labs(y = "比例", x = "变量") +
  theme_minimal() +
  theme(
    legend.position = "right",
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.margin = margin(t = 20, r = 20, b = 20, l = 20)
  )

关键细节说明 #

1. 数据转换：使用pivot_longer将多列变量合并为"变量-响应"的长格式，同时统一X4的文本格式，避免因大小写导致的类别拆分。
2. 调色板设计：为三类变量分别设置差异化色系：Y/N用蓝橙对比色、Old/Young用绿红对比色、Likert量表用灰度渐变，直观区分不同变量类型的响应。
3. 图例优化：通过interaction绑定响应与变量类型，再拆分标签只显示响应值，同时在图表顶部标注变量类型，解决不同类型变量的图例区分问题。
4. 百分比堆叠：使用position = "fill"将条形图转换为百分比比例，便于跨变量的类别分布对比。

内容的提问来源于stack exchange，提问作者EB3112