如何使用ggplot2为指定区域内的点和背景着色

步骤1：预处理数据，标记点的位置 #

先给数据集添加一列，判断每个点是否落在两条灰色参考线（y = x ± s_est）之间：

library(dplyr)
library(ggplot2)

# 加载数据和s_est值
df <- structure(list(real = c(3.33, 5.92, 5.3, 6, 6.96, 7.03, 6.6, 
7.92, 8.3, 10.52, 6.34, 4.38, 4.59, 9.8, 10.3, 10, 8.25, 6, 7.44, 
6.66, 9.09, 9.22, 9.7, 4.82, 6.1, 4.92, 4.29, 3.22, 6.01, 9.05, 
9.04, 4.85, 8.22, 6.7, 6.7, 4.62, 4.82, 8.52, 5.24, 8.15, 7, 
10, 7, 5.18, 5.93, 8.4, 7.7, 7.24, 9.54, 6.06, 8, 4.35, 4.2, 
4.51, 2.48, 9.1, 5.34, 4.19, 8.05, 8.55, 6.55, 11.4, 10.96, 9.64, 
4.49, 6, 6.9, 6.17, 9, 6.92, 3.77, 4.22, 8.92, 7.55, 7.6, 6.82, 
5.32, 8.39, 5.09, 10.96, 6.68, 9.4, 5.04, 5.59, 9.21, 9.7, 6.98, 
6.17, 8.89, 9.74, 6.08, 6.7, 4.41, 3.57, 7.12, 6.09, 6.11, 6.82, 
7.3, 6.77), predicted = c(3.3049898147583, 7.57794666290283, 
5.81329345703125, 3.71067190170288, 6.35026741027832, 6.59200620651245, 
6.32752990722656, 7.13449430465698, 7.78791570663452, 8.61589622497559, 
7.72269868850708, 5.33322525024414, 7.26069974899292, 9.23727989196777, 
8.27904891967773, 7.55226612091064, 5.94742393493652, 4.07633399963379, 
7.67468595504761, 5.64575576782227, 7.85368394851685, 7.73117685317993, 
10.2843132019043, 4.96891403198242, 6.29262351989746, 6.03091764450073, 
6.71697568893433, 3.50744342803955, 6.46608829498291, 8.20327758789062, 
7.52885150909424, 4.58155632019043, 6.1530909538269, 6.49482202529907, 
5.28225088119507, 4.44094896316528, 5.503089427948, 7.79408073425293, 
5.6220269203186, 7.12402009963989, 6.30716276168823, 7.15596580505371, 
7.26271867752075, 5.41359615325928, 5.68268489837646, 6.81329536437988, 
7.10254955291748, 8.64251136779785, 8.65674114227295, 5.94885206222534, 
9.24687099456787, 5.93400239944458, 5.66134691238403, 6.14793062210083, 
2.94440221786499, 9.21078777313232, 5.96825170516968, 4.69157028198242, 
7.91313886642456, 6.90836668014526, 6.72082805633545, 9.95611953735352, 
9.15732383728027, 6.68948268890381, 3.60811305046082, 7.42742109298706, 
6.05647945404053, 6.2350025177002, 8.12950134277344, 7.56590843200684, 
5.3975772857666, 3.48417925834656, 7.63604927062988, 8.04048824310303, 
7.78053188323975, 7.34217929840088, 7.93345308303833, 8.03125, 
5.62498426437378, 4.80621385574341, 5.19631958007812, 7.51661252975464, 
5.43919944763184, 5.5195426940918, 6.10152912139893, 8.25357818603516, 
5.73111486434937, 7.27180528640747, 8.37008285522461, 7.78157567977905, 
7.52273559570312, 4.32158374786377, 6.20211696624756, 4.30103015899658, 
7.89811611175537, 6.88143062591553, 6.74230575561523, 6.75651741027832, 
6.64747190475464, 6.72232007980347)), class = c("tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -100L))

s_est = 4.536

# 添加分组列
df <- df %>%
  mutate(in_range = ifelse(predicted >= real - s_est & predicted <= real + s_est, 
                          "区域内", "区域外"))

步骤2：生成带状高亮区域的数据 #

高亮区域是两条斜线之间的带状区域，用geom_ribbon实现更准确，先生成对应的数据：

ribbon_data <- data.frame(
  x = seq(min(df$real), max(df$real), length.out = 100),
  ymin = seq(min(df$real), max(df$real), length.out = 100) - s_est,
  ymax = seq(min(df$real), max(df$real), length.out = 100) + s_est
)

步骤3：绘制最终可视化图 #

按图层顺序绘制（背景优先，再画点和线）：

ggplot(df, aes(x = real, y = predicted)) +
  # 画高亮背景带
  geom_ribbon(data = ribbon_data, aes(x = x, ymin = ymin, ymax = ymax), 
              fill = "#cce5ff", alpha = 0.3) +
  # 画点，按分组设置颜色
  geom_point(aes(color = in_range), size = 2) +
  # 画参考线
  geom_abline(intercept = 0, slope = 1, color = "black", linewidth = 0.8) +
  geom_abline(intercept = s_est, slope = 1, color = "darkgrey", linetype = "dashed") +
  geom_abline(intercept = -s_est, slope = 1, color = "darkgrey", linetype = "dashed") +
  # 主题与标题
  theme_classic() +
  ggtitle("Test Set") +
  # 自定义颜色
  scale_color_manual(values = c("区域内" = "#2ecc71", "区域外" = "#e74c3c")) +
  # 调整图例标签
  labs(color = "点位置")

说明 #

• geom_ribbon用于绘制两条斜线之间的填充区域，alpha参数控制透明度，避免遮挡点
• 点的颜色通过aes(color = in_range)绑定分组列，再用scale_color_manual自定义颜色
• 灰色参考线设置为虚线，更易区分主参考线

内容的提问来源于stack exchange，提问作者christine