如何用循环遍历星期几简化R语言数据统计与可视化代码？

需求说明 #

刚学习R语言两周，现有绘图代码通过硬编码编写了多条annotate语句添加注释，希望优化实现：

• 自动计算minutesworn列按weekday分组后的均值最大值
• 将该最大值加上指定偏移量后，作为所有注释的统一y轴坐标，替代重复的annotate语句

现有代码与数据集 #

数据集 #

data_df <- tibble::tribble(
  ~id,        ~activitydate,         ~totalsteps, ~totaldistance,   ~sedentaryminutes, ~calories, ~activeminutes, ~totalminutesasleep, ~totaltimeinbed, ~timeawakeinbed, ~month,  ~weekday,    ~minutesworn, ~alldaywear,
  1503960366, as.Date("2016-04-12"), 13162,       8.5,              728,               1985,      366,            327,                 346,             19,              "April", "Tuesday",   1094,         TRUE,
  1503960366, as.Date("2016-04-13"), 10735,       6.96999979019165, 776,               1797,      257,            384,                 407,             23,              "April", "Wednesday", 1033,         TRUE,
  1503960366, as.Date("2016-04-15"), 9762,        6.28000020980835, 726,               1745,      272,            412,                 442,             30,              "April", "Friday",    998,          TRUE,
  1503960366, as.Date("2016-04-16"), 12669,       8.15999984741211, 773,               1863,      267,            340,                 367,             27,              "April", "Saturday",  1040,         TRUE,
  1503960366, as.Date("2016-04-17"), 9705,        6.48000001907349, 539,               1728,      222,            700,                 712,             12,              "April", "Sunday",    761,          TRUE,
  1503960366, as.Date("2016-04-19"), 15506,       9.88000011444092, 775,               2035,      345,            304,                 320,             16,              "April", "Tuesday",   1120,         TRUE,
  1503960366, as.Date("2016-04-20"), 10544,       6.67999982833862, 818,               1786,      245,            360,                 377,             17,              "April", "Wednesday", 1063,         TRUE,
  1503960366, as.Date("2016-04-21"), 9819,        6.34000015258789, 838,               1775,      238,            325,                 364,             39,              "April", "Thursday",  1076,         TRUE,
)

现有分析与绘图代码 #

# 查找均值的最大值
data_df %>% 
  group_by(weekday) %>% 
  summarize(max(mean(minutesworn)))

# 绘图
data_df %>% 
  group_by(weekday) %>% 
  summarize(mean_wear = mean(minutesworn)) %>% 
  ggplot(mapping = aes(x = factor(weekday, level =
                                c('Sunday', 'Monday', 'Tuesday',
                                  'Wednesday', 'Thursday', 'Friday',
                                  'Saturday')), y = mean_wear, fill = weekday)) +
geom_col() +
labs(title = "Minutes Worn by Weekday",
   caption = "Data Collected in 2016") +
xlab("Weekday") + ylab("Average Minutes Worn") +
annotate("text", x = "Friday", y = 1052, label = "Friday") +
annotate("text", x = "Saturday", y = 1022, label = "Saturday") +
annotate("text", x = "Sunday", y = 977, label = "Sunday") +
annotate("text", x = "Monday", y = 1040, label = "Monday") +
annotate("text", x = "Tuesday", y = 1057, label = "Tuesday") +
annotate("text", x = "Wednesday", y = 1010, label = "Wednesday") +
annotate("text", x = "Thursday", y = 1008, label = "Thursday")

优化后的代码 #

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

# 1. 预处理数据：计算分组均值，设置星期顺序
summary_df <- data_df %>%
  group_by(weekday) %>%
  summarize(mean_wear = mean(minutesworn)) %>%
  mutate(weekday = factor(weekday, level = c('Sunday', 'Monday', 'Tuesday', 
                                             'Wednesday', 'Thursday', 'Friday', 'Saturday'))) %>%
  arrange(weekday)

# 2. 计算注释的y轴坐标：均值最大值 + 自定义偏移量（可按需调整）
offset <- 30
annotate_y <- max(summary_df$mean_wear) + offset

# 3. 绘图并添加注释
ggplot(summary_df, aes(x = weekday, y = mean_wear, fill = weekday)) +
  geom_col() +
  # 用geom_text替代重复的annotate，直接映射数据生成注释
  geom_text(aes(label = weekday), y = annotate_y) +
  labs(title = "Minutes Worn by Weekday",
       caption = "Data Collected in 2016",
       x = "Weekday",
       y = "Average Minutes Worn") +
  # 可选：扩展y轴范围，避免注释超出画布
  expand_limits(y = annotate_y + offset/2)

优化亮点 #

• 消除重复代码：用一行geom_text替代7条重复的annotate语句，代码更简洁易维护
• 自动计算坐标：无需硬编码y值，通过max()获取均值最大值，结合偏移量自动生成注释位置
• 保留自定义顺序：提前对weekday设置因子水平，确保绘图顺序符合需求
• 灵活性高：偏移量offset可根据可视化需求调整，控制注释与柱子顶部的距离

内容的提问来源于stack exchange，提问作者Cyris Zeiders