如何用mutate_at和if_else批量替换多列NA值为对应_max列值？

先解决基础报错问题 #

报错could not find function "%>%"是因为未加载dplyr或tidyverse工具包，先执行以下代码加载依赖：

library(tidyverse)

完整批量处理代码 #

以下代码可自动适配所有以value开头的列，无需手动指定数百个列名：

# 加载必要工具包
library(tidyverse)

# 示例数据
group1 = c(1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2)
group2 = c(1,1,1,2,2,2,3,3,3,1,1,1,2,2,2,3,3,3)
group3 = c(NA,0,1,NA,0,1,NA,0,1,NA,0,1,NA,0,1,NA,0,1)
value1 = c(100,NA,NA,500,600,400,NA,NA,100,150,NA,NA,600,700,500,NA,NA,200)
value2 = c(100,200,150,200,300,500,NA,NA,NA,200,400,300,400,600,100,NA,NA,NA)
value3 = c(100,12,234,500,600,400,345,345,100,150,234,354,600,700,500,325345,324,200)
df = data.frame(group1=group1, group2=group2, group3=group3, value1=value1, value2=value2, value3=value3)

# 预期结果数据框
group1_ = c(1,1,1,1,1,1,2,2,2,2,2,2)
group2_ = c(1,1,2,2,3,3,1,1,2,2,3,3)
group3_ = c(0,1,0,1,0,1,0,1,0,1,0,1)
value1_ = c(100,100,600,400,NA,100,150,150,700,500,NA,200)
value2_ = c(200,150,300,500,NA,NA,400,300,600,100,NA,NA)
value3_ = c(100,234,600,400,345,100,234,354,700,500,325345,200)
df_wanted = data.frame(group1=group1_, group2=group2_, group3=group3_, value1=value1_, value2=value2_, value3=value3_)

# 批量处理逻辑
df_processed <- df %>%
  # 替换group3列的NA为0
  mutate(group3 = if_else(is.na(group3), 0, group3)) %>%
  # 按group1/group2/group3分组，取各列最大值
  group_by(group1, group2, group3) %>%
  summarise(across(everything(), ~max(., na.rm = TRUE)), .groups = 'drop') %>%
  # 将max计算产生的-Inf转回NA
  na_if(-Inf) %>%
  # 按group1/group2分组，为所有value开头的列生成对应_max后缀的最大值列
  group_by(group1, group2) %>%
  mutate(across(starts_with("value"), ~max(., na.rm = TRUE), .names = "{.col}_max")) %>%
  # 再次处理max计算产生的-Inf
  na_if(-Inf) %>%
  # 批量替换每个value列的NA为对应的_max列的值
  mutate(across(starts_with("value"), 
                ~if_else(is.na(.), get(str_c(cur_column(), "_max")), .))) %>%
  # 可选：删除临时生成的_max列（不需要保留可执行此行）
  select(-ends_with("_max"))

# 验证结果是否匹配预期
all.equal(df_processed, df_wanted)

核心批量处理逻辑说明 #

• 使用starts_with("value")自动匹配所有以value开头的列，无需手动枚举数百个列名
• across的.names参数自动生成带_max后缀的分组最大值列
• 通过cur_column()动态获取当前处理的列名，配合get()调用对应_max列实现NA替换
• 全程使用tidyverse现代语法，替代已淘汰的mutate_at，兼容性和可读性更强

内容的提问来源于stack exchange，提问作者Alibek Galiyev