如何在R中绘制二元变量共现实例数量统计图？

Absolutely可以实现！你想要展示的是0/1因子变量两两同时取1的实例数量，最适合的可视化方式是热力图（清晰展示所有两两组合的数值），也可以用网络图来突出关联强弱。我会用ggplot2和tidyverse工具帮你完成，步骤很清晰：

1. 数据预处理：将因子转为数值型 #

因为因子类型无法直接参与计算，我们先把所有列转成数值型的0/1：

# 加载你的数据集
df <- structure(list(english = structure(c(2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L), .Label = c("0", "1"), class = "factor"), math = structure(c(2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L), .Label = c("0", "1"), class = "factor"), science = structure(c(1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L), .Label = c("0", "1"), class = "factor"), history = structure(c(2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("0", "1"), class = "factor"), art = structure(c(2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L), .Label = c("0", "1"), class = "factor"), geography = structure(c(1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L), .Label = c("0", "1"), class = "factor")), row.names = c(NA, -11L), class = c("tbl_df", "tbl", "data.frame"))

# 把所有因子列转为数值型（0/1）
library(dplyr)
df_num <- df %>% mutate(across(everything(), ~ as.numeric(as.character(.x))))

2. 计算两两变量的共现次数矩阵 #

这里用crossprod()超级高效，因为两个0/1向量的点积刚好就是它们同时为1的实例数：

# 计算共现矩阵
co_occur <- crossprod(df_num)

# 转成ggplot需要的长格式
library(tidyr)
co_occur_long <- co_occur %>% 
  as.data.frame() %>% 
  rownames_to_column("var1") %>% 
  pivot_longer(cols = -var1, names_to = "var2", values_to = "count")

3. 用ggplot2绘制热力图 #

每个单元格的颜色深浅和内部数字对应共现次数，直观清晰：

library(ggplot2)

ggplot(co_occur_long, aes(x = var1, y = var2, fill = count)) +
  geom_tile(color = "white") + # 白色边框区分每个单元格
  geom_text(aes(label = count), color = "black", size = 4) + # 显示具体数值
  scale_fill_gradient(low = "#f0f9e8", high = "#006d2c") + # 渐变配色，浅到深绿
  labs(title = "变量同时取1的实例数量热力图",
       x = "", y = "", fill = "共现次数") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) # x轴标签倾斜，避免重叠

在这个图里，你能直接看到english和math的共现次数是5，和你手动计算的结果完全一致。

可选：用网络图展示关联强度 #

如果想要更直观地体现变量间的关联紧密程度，可以用igraph包绘制网络图：

library(igraph)

# 整理网络图数据（去掉对角线和重复的边）
graph_data <- co_occur_long %>% 
  filter(var1 < var2) %>% 
  filter(count > 0)

# 构建并绘制网络图
g <- graph_from_data_frame(graph_data, directed = FALSE)
plot(g, 
     edge.width = E(g)$count, # 边越粗代表共现次数越多
     vertex.size = 20,
     vertex.label.cex = 0.8,
     edge.color = "#006d2c",
     main = "变量共现次数网络图")

两种可视化方式都能完美满足你的需求，按需选择就好！

内容的提问来源于stack exchange，提问作者Vale Y