使用ggplot绘制带正确分箱标签的彩虹色直方图求助

问题原因 #

标签错乱是因为原有代码中fill = cut(V1, 25)的分组逻辑和geom_histogram、stat_bin默认的分箱逻辑不统一，导致每个分箱上叠加了多个重复标签。

解决代码 #

先构造示例数据集，再运行绘图代码即可同时实现彩虹渐变填充、正常分箱标签、隐藏0计数标签三个需求：

library(ggplot2)
# 构造示例数据集
final_df <- structure(list(V1 = c(18, 0, 20, 21, 0, 2, 0, 1, 0, 0, 4, 16, 
0, 0, 20, 20, 2, 0, 19, 22, 0, 0, 19, 0, 22, 22, 19, 2, 0, 0, 
1, 18, 23, 1, 3, 1, 1, 1, 0, 21, 21, 0, 0, 15, 24, 0, 20, 19, 
0, 1, 20, 21, 0, 0, 20, 22, 20, 0, 21, 0, 0, 22, 0, 0, 0, 23, 
2, 1, 1, 21, 0, 2, 3, 23, 23, 1, 22, 0, 19, 23, 1, 2, 23, 1, 
0, 0, 20, 1, 0, 0, 1, 18, 0, 0, 0, 0, 0, 2, 0, 7, 22, 0, 0, 23, 
1, 0, 23, 0, 0, 1, 2, 0, 0, 18, 16, 0, 0, 1, 0, 0, 0, 2, 22, 
0, 2, 0, 0, 0, 24, 0, 0, 0, 1, 1, 20, 0, 0, 1, 18, 0, 1, 1, 0, 
0, 3, 0, 20, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 20, 2, 
0, 1, 22, 0, 1, 23, 2, 0, 1, 5, 0, 10, 1, 17, 0, 0, 1, 1, 2, 
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 2, 0, 23, 2, 19, 2, 1, 21, 3, 
0, 0, 20, 0, 1, 0, 1, 0, 0, 24, 2, 1, 1, 23, 1, 1, 0, 1, 0, 0, 
22, 23, 0, 23, 0, 22, 2, 19, 0, 20, 22, 0, 23, 0, 21, 0, 0, 23, 
0, 0, 0, 0, 3, 22, 1, 0, 1, 22, 22, 20, 0, 1, 2, 22, 2, 23, 0, 
18, 1, 23, 0, 2, 0, 1, 22, 0, 21, 0, 2, 20, 0, 0, 23, 0, 1, 18, 
0, 18, 20, 1, 0, 20, 0, 1, 0, 0, 17, 20, 0, 0, 1, 22, 20, 22, 
2, 1, 1, 0, 1, 0, 0, 0, 18, 0, 0, 21, 0, 0, 2, 22, 20, 1, 0, 
0, 0, 0, 1, 0, 0, 1, 0, 4, 1, 0, 21, 21, 0, 0, 1, 0, 1, 3, 0, 
1, 1, 0, 24, 0, 0, 22, 17, 0, 1, 20, 1, 1, 21, 1, 21, 21, 0, 
21, 0, 1, 23, 0, 0, 23, 21, 0, 0, 24, 0, 6, 17, 0, 21, 0, 23, 
0, 0, 22, 1, 1, 22, 0, 2, 0, 0, 1, 19, 0, 21, 21, 2, 1, 18, 1, 
21, 0, 1, 1, 0, 0, 1, 23, 0, 0, 1, 0, 0, 0, 1, 2, 1, 0, 0, 0, 
25, 0, 0, 1, 0, 0, 0, 23, 23, 0, 0, 0, 21, 19, 2, 0, 0, 0, 0, 
0, 1, 0, 22, 22, 0, 19, 0, 3, 0, 21, 0, 1, 20, 1, 1, 1, 22, 1, 
22, 1, 22, 1, 0, 2, 0, 25, 23, 0, 20, 0, 2, 22, 0, 0, 1, 0, 1, 
23, 22, 0, 1, 19, 23, 1, 0, 2, 0, 18, 0, 0, 2, 0, 0, 23, 0, 0, 
0, 0, 0, 1, 2, 1, 0, 21, 0, 21, 20, 0, 1, 19, 23, 0, 1, 23, 0, 
1, 22, 21, 3, 0, 22, 2, 0, 1, 23, 2, 0, 24, 23, 21, 23, 20, 0, 
0, 0, 20, 22, 0, 2, 0, 17, 0, 0, 1, 22, 1, 1, 1, 0, 0, 3, 3, 
5, 21, 21, 1, 19, 18, 0, 24, 1, 2, 0, 0, 1, 1, 0, 0, 0, 0, 0, 
0, 23, 1, 20, 0, 0, 1, 19, 22, 21, 24, 3, 1, 2, 24, 0, 0, 23, 
17, 22, 0, 24, 23, 16, 1, 0, 2, 20, 0, 19, 0, 2, 1, 22, 20, 0, 
20, 0, 1, 22, 0, 1, 0, 2, 0, 1, 0, 0, 2, 25, 24, 2, 20, 3, 0, 
0, 23, 0, 4, 0, 19, 1, 0, 1, 0, 3, 19, 22, 0, 0, 0, 1, 0, 1, 
23, 20, 20, 23, 0, 0, 0, 24, 0, 21, 20, 23, 0, 1, 1, 0, 19, 0, 
0, 0, 1, 22, 0, 22, 0, 1, 18, 0, 20, 1, 0, 0, 1, 20, 0, 0, 0, 
0, 0, 0, 0, 0, 19, 0, 0, 1, 0, 2, 23, 19, 21, 4, 1, 0, 0, 1, 
23, 21, 21, 4, 20, 24, 0, 3, 0, 20, 23, 1, 23, 21, 20, 18, 0, 
21, 2, 1, 21, 0)), class = "data.frame", row.names = c(NA, -713L
))

# 绘图代码
ggplot(final_df,aes(x=V1)) + 
  geom_histogram(aes(fill = after_stat(x)), bins = 25, show.legend = FALSE) +
  scale_fill_gradientn(colours = rainbow(25)) +
  stat_bin(aes(y = after_stat(count), 
               label = ifelse(after_stat(count) > 0, after_stat(count), "")),
           geom = "text", vjust = -.5, bins = 25)

核心修改逻辑 #

• 所有涉及分箱的图层统一指定bins=25，保证分箱规则完全一致，从根源解决标签错乱问题
• 直接用分箱后的x值映射填充色，搭配scale_fill_gradientn调用rainbow()生成彩虹渐变效果，无需提前对原始数据做cut处理
• 标签映射时添加ifelse判断，计数为0的分箱返回空文本，自动隐藏不需要的标签

内容的提问来源于stack exchange，提问作者neuron