基于两列高亮重复行：无需手动指定颜色与行的实现方案

我有一个数据集需要转换为表格，要求当ID与timepoint同时相同时，将对应的行组（成对或成组）用颜色高亮，且不同行组使用不同颜色。现有代码能实现功能，但需要手动指定颜色列表和行，无法适配不同数据集，求通用方法。

提供的数据框如下：

id_table <- structure(list(ID = c("168", "168", "168", "002", "002", "002", "002", "002", "002", "002 15/5/13", "002 15/5/13", "062", "062", "062+2 (11/02/14)", "062+2 (11/02/14)", "074", "074", "074", "074", "074", "074", "074", "074", "093", "093", "093", "093", "093", "093", "093", "093", "105", "105", "105", "105", "105", "105", "105", "105", "127", "127", "142", "142", "142", "142", "145", "145", "149", "149", "149", "149", "155", "155", "155", "155", "155", "155", "156", "156", "156", "156", "158", "158", "158", "158", "168", "168", "174", "174", "180", "180", "183", "183", "201", "201", "205", "205"), timepoint = c("1", "1", "1", "3", "3", "5", "5", "7", "7", NA, NA, "5", "5", "1", "1", "2", "2", "4", "4", "5", "5", "7", "7", "2", "2", "3", "3", "5", "5", "7", "7", "2", "2", "3", "3", "5", "5", "7", "7", "3", "3", "1", "1", "3", "3", "1", "1", "1", "1", "3", "3", "1", "1", "3", "3", "7", "7", "3", "3", "5", "5", "1", "1", "3", "3", "3", "3", "5", "5", "1", "1", "1", "1", "1", "1", "1", "1"), Plate = c("Plate_7", "Plate_3", "Plate_6", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_7", "Plate_1", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_7", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_1", "Plate_7", "Plate_2", "Plate_7", "Plate_2", "Plate_7", "Plate_2", "Plate_7", "Plate_2", "Plate_2", "Plate_7", "Plate_7", "Plate_2", "Plate_7", "Plate_2", "Plate_3", "Plate_7", "Plate_6", "Plate_3", "Plate_6", "Plate_3", "Plate_6", "Plate_3", "Plate_3", "Plate_6", "Plate_3", "Plate_6", "Plate_6", "Plate_3", "Plate_3", "Plate_6", "Plate_6", "Plate_3", "Plate_7", "Plate_6", "Plate_4", "Plate_5", "Plate_4", "Plate_5", "Plate_3", "Plate_6", "Plate_6", "Plate_3", "Plate_6", "Plate_3", "Plate_4", "Plate_5", "Plate_3", "Plate_6", "Plate_3", "Plate_7", "Plate_7", "Plate_5", "Plate_5", "Plate_7"), `Year Run` = c(2022, 2020, 2022, 2020, 2022, 2020, 2022, 2022, 2020, 2020, 2022, 2020, 2022, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2022, 2020, 2020, 2022, 2022, 2020, 2022, 2020, 2020, 2022, 2022, 2020, 2022, 2020, 2022, 2020, 2020, 2022, 2020, 2022, 2022, 2020, 2020, 2022, 2022, 2020, 2022, 2022, 2022, 2022, 2022, 2022, 2020, 2022, 2022, 2020, 2022, 2020, 2022, 2022, 2020, 2022, 2020, 2022, 2022, 2022, 2022, 2022)), row.names = c(NA, -77L), class = c("tbl_df", "tbl", "data.frame"))

现有需手动配置的非通用代码：

color_scheme <- c("#DDDDDD", "#AAAAAA", "#777777", "#444444", "#111111")

# Create a grouping variable based on ID and Timepoint
group_var <- paste(id_table$ID, id_table$timepoint, sep = "_")

# Create a color vector based on the grouping variable
color_var <- as.numeric(factor(group_var))

# Generate the table and highlight rows based on the color vector
id_table <- id_table %>%
  select(-ID) %>%
  kbl() %>%
  row_spec(which(color_var == 1), background = color_scheme[1]) %>%
  row_spec(which(color_var == 2), background = color_scheme[2]) %>%
  row_spec(which(color_var == 3), background = color_scheme[3]) %>%
  row_spec(which(color_var == 4), background = color_scheme[4]) %>%
  row_spec(which(color_var == 5), background = color_scheme[5])

# Print the table
id_table

核心逻辑是自动处理分组、配色和行样式，无需手动指定每个分组的参数：

library(knitr)
library(kableExtra)
library(dplyr)

# 1. 生成分组键，处理timepoint中的NA值
id_table <- id_table %>%
  mutate(group_key = paste(ID, coalesce(timepoint, "NA"), sep = "_"))

# 2. 获取唯一分组并自动生成对应数量的颜色
unique_groups <- unique(id_table$group_key)
num_groups <- length(unique_groups)
# 可选配色方案：灰色渐变、彩虹色、viridis调色板等
color_scheme <- gray.colors(num_groups, start = 0.9, end = 0.3)
# color_scheme <- rainbow(num_groups)
# color_scheme <- viridis::viridis(num_groups)

# 3. 创建初始表格
table_output <- id_table %>%
  select(-ID, -group_key) %>%
  kbl()

# 4. 循环批量设置行背景色
for (i in seq_along(unique_groups)) {
  target_rows <- which(id_table$group_key == unique_groups[i])
  table_output <- table_output %>%
    row_spec(target_rows, background = color_scheme[i])
}

# 输出最终表格
table_output

关键优化点 #

• 自动分组：用coalesce将timepoint的NA转为字符串"NA"，确保缺失值也能被正确分组
• 动态配色：根据数据集的唯一分组数量自动生成颜色列表，支持任意大小的数据集
• 批量处理：通过循环自动为每个分组应用行样式，避免手动重复编写row_spec调用

内容的提问来源于stack exchange，提问作者Gabriella