如何在ggplot中让geom_text数值标签与对应深蓝色柱形对齐？

问题描述 #

使用ggplot绘制分组柱形图时，geom_text添加的数值标签本应显示在深蓝色（对应ende_abs指定的2020队列）柱形上方，但实际错位显示在左侧柱形上方。

数据集与原代码 #

数据集 #

df <- structure(list(label2plot = structure(c(1L, 2L, 1L, 2L, 1L, 2L, 
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L
), levels = c("aaa", "bbb"), class = c("ordered", "factor")), 
    var_abs = c(717L, 569L, 860L, 752L, 713L, 575L, 918L, 724L, 
    946L, 764L, 951L, 764L, 784L, 691L, 672L, 610L, 833L, 671L, 
    773L, 620L, 532L, 293L), var_rel = c(0.557542768273717, 0.442457231726283, 
    0.533498759305211, 0.466501240694789, 0.553571428571429, 
    0.446428571428571, 0.559074299634592, 0.440925700365408, 
    0.553216374269006, 0.446783625730994, 0.554518950437318, 
    0.445481049562682, 0.531525423728814, 0.468474576271186, 
    0.52418096723869, 0.47581903276131, 0.553856382978723, 0.446143617021277, 
    0.554917444364681, 0.445082555635319, 0.644848484848485, 
    0.355151515151515), cohort = structure(c(11L, 11L, 10L, 10L, 
    9L, 9L, 8L, 8L, 7L, 7L, 6L, 6L, 5L, 5L, 4L, 4L, 3L, 3L, 2L, 
    2L, 1L, 1L), levels = c("2010", "2011", "2012", "2013", "2014", 
    "2015", "2016", "2017", "2018", "2019", "2020"), class = "factor")), row.names = c(NA, 
-22L), class = "data.frame")

titel <- "ccc"
subtitel <- " "
werte <- c("aaa", "bbb")
start_abs <- "2010"
ende_abs <- "2020"
semvorende_abs <- "2019" # 补充原代码缺失的变量

原绘图代码 #

ggplot() +
  geom_bar (
    data = df,
    aes(
      x = factor(label2plot, levels = werte),
      y = var_rel,
      group = cohort,
      fill = forcats::fct_other(cohort, ende_abs, other_level = start_abs)
    ),
    stat = "identity",
    position = position_dodge()
  ) +
  scale_y_continuous(labels = scales::percent, limits = c(0, 1)) +
  theme_classic() +
  theme(
    legend.position = "bottom",
    plot.title = element_text(hjust = 0.5,
                              size = 14,
                              face = "bold"),
    plot.subtitle = element_text(hjust = 0.5),
    plot.caption = element_text(hjust = 0.5),
  ) +
  geom_text(
    size = 3,
    position = position_dodge2(preserve = 'single', width = 0.9),
    hjust = 0.5,
    vjust = -1,
    color = "black",
    aes(
      x = df$label2plot,
      y = df$var_rel,
      label = ifelse(df$cohort == ende_abs, paste0(sprintf(
        "%.1f", df$var_rel * 100
      ), "%"), "")
    )
  ) +
  scale_fill_manual(
    values = c("#AFCDE4", "#389DC3"),
    limits = c(start_abs, ende_abs),
    labels = c(paste0(start_abs, " - ", semvorende_abs), ende_abs)
  ) +
  labs(
    title = str_wrap(titel, 45),
    x = "",
    y =  "",
    fill = "Cohort"
  )

问题原因 #

• geom_text缺失group映射：原geom_bar通过group = cohort实现分组，但geom_text未同步该映射，导致标签无法和对应分组柱形对齐。
• 直接用df$xxx破坏映射逻辑：ggplot要求在aes内使用变量名而非数据框索引，否则会丢失分组关联信息。
• position参数不匹配：geom_bar用position_dodge()，geom_text却用position_dodge2，两者位置计算逻辑不一致，导致错位。

修正后的代码 #

library(ggplot2)
library(forcats)
library(stringr)

ggplot(df) +
  geom_bar (
    aes(
      x = factor(label2plot, levels = werte),
      y = var_rel,
      group = cohort,
      fill = forcats::fct_other(cohort, ende_abs, other_level = start_abs)
    ),
    stat = "identity",
    position = position_dodge(width = 0.9) # 统一宽度参数
  ) +
  scale_y_continuous(labels = scales::percent, limits = c(0, 1)) +
  theme_classic() +
  theme(
    legend.position = "bottom",
    plot.title = element_text(hjust = 0.5, size = 14, face = "bold"),
    plot.subtitle = element_text(hjust = 0.5),
    plot.caption = element_text(hjust = 0.5)
  ) +
  geom_text(
    data = subset(df, cohort == ende_abs), # 仅筛选目标队列数据
    aes(
      x = factor(label2plot, levels = werte),
      y = var_rel,
      group = cohort, # 添加分组映射
      label = paste0(sprintf("%.1f", var_rel * 100), "%")
    ),
    size = 3,
    position = position_dodge(width = 0.9), # 和geom_bar的position参数匹配
    hjust = 0.5,
    vjust = -1,
    color = "black"
  ) +
  scale_fill_manual(
    values = c("#AFCDE4", "#389DC3"),
    limits = c(start_abs, ende_abs),
    labels = c(paste0(start_abs, " - ", semvorende_abs), ende_abs)
  ) +
  labs(
    title = str_wrap(titel, 45),
    x = "",
    y = "",
    fill = "Cohort"
  )

关键修改说明 #

• 给geom_text添加group = cohort映射，确保标签和对应分组柱形关联。
• 统一geom_bar和geom_text的position_dodge(width = 0.9)参数，保证位置完全对齐。
• 用subset(df, cohort == ende_abs)筛选目标数据，避免无效计算，同时不再使用df$xxx的索引方式。
• 移除ifelse判断，简化代码逻辑。

内容的提问来源于stack exchange，提问作者Dierforth