如何用ifelse封装字符串提取函数实现灵活单位映射与非覆盖赋值？

示例数据 #

现有如下示例数据：

library(data.table)
example_dat <- fread("var_nam description
      some_var this_is_some_var_kg
      other_var this_is_meters_for_another_var
      extra_var the_price_of_apples
      another_var cost_of_goods_sold")
example_dat$description  <- gsub("_", " ", example_dat$description)

# 处理后的数据：
#        var_nam                    description
# 1:    some_var            this is some var kg
# 2:   other_var this is meters for another var
# 3:   extra_var            the price of apples
# 4: another_var             cost of goods sold

vector_of_units <- c("kg", "meters", "var")

已有解决方案 #

此前已有两种匹配单位并新增列的方案：

1. 提取所有匹配项（maydin方案）：

library(tidyverse)
setDT(example_dat)[, unit :=    unlist(lapply(example_dat$description,function(x) 
                    paste0(vector_of_units[str_detect(x,vector_of_units)],
                    collapse = ",")))]

# 输出结果：
#        var_nam                    description       unit
# 1:    some_var            this is some var kg     kg,var
# 2:   other_var this is meters for another var meters,var
# 3:   extra_var            the price of apples           
# 4: another_var             cost of goods sold         

2. 提取第一个匹配项（langtang方案，更贴合需求）：

example_dat[, unit:=stringr::str_extract(description, paste0(vector_of_units,collapse = "|"))]

# 输出结果：
#        var_nam                    description   unit
# 1:    some_var            this is some var kg    var
# 2:   other_var this is meters for another var meters
# 3:   extra_var            the price of apples   <NA>
# 4: another_var             cost of goods sold   <NA>

需求与问题 #

需要实现更灵活的匹配逻辑：

• 分别定义匹配向量和输出向量，实现匹配值到目标值的映射：

vector_of_units_in <- c("kg", "meters", "var")
vector_of_units_out <- c("kilogram", "meters", "variable")

vector_of_units_euro <- c("cost", "price")
vector_of_units_euro_out <- "euro"

• 无匹配时不覆盖原有值（避免用<NA>替换已存在的有效值）

尝试基于langtang方案改写后得到错误结果：

setDT(example_dat)[, unit := ifelse(!is.na(stringr::str_extract(description, vector_of_units_in)), paste0(vector_of_units_out, collapse = "|"), NA)]

# 尝试补充欧元匹配逻辑
setDT(example_dat)[, unit := ifelse(!is.na(stringr::str_extract(description, vector_of_units_euro)), paste0(vector_of_units_euro_out, collapse = "|"), unit)]

错误输出：

var_nam                    description                     unit
1:    some_var            this is some var kg kilogram|meters|variable
2:   other_var this is meters for another var kilogram|meters|variable
3:   extra_var            the price of apples                     <NA>
4: another_var             cost of goods sold                     <NA>

期望得到如下输出：

var_nam                    description       unit
1:    some_var            this is some var kg     kilogram
2:   other_var this is meters for another var     meters
3:   extra_var            the price of apples     euro      
4: another_var             cost of goods sold     euro    

正确实现方案 #

可以通过构建匹配映射字典，结合字符串提取和条件赋值实现，以下是两种可行方案：

方案1：使用dplyr+stringr实现 #

library(dplyr)
library(stringr)

# 构建完整的匹配映射表
match_map <- tibble(
  pattern = c(vector_of_units_in, vector_of_units_euro),
  output = c(vector_of_units_out, rep(vector_of_units_euro_out, length(vector_of_units_euro)))
)

# 生成匹配正则表达式（按字典顺序匹配，可调整顺序修改优先级）
match_pattern <- str_c(match_map$pattern, collapse = "|")

example_dat <- example_dat %>%
  mutate(
    # 提取匹配的原始值
    matched_val = str_extract(description, match_pattern),
    # 根据映射替换目标值，无匹配则保留原有unit值
    unit = case_when(
      !is.na(matched_val) ~ match_map$output[match(matched_val, match_map$pattern)],
      TRUE ~ unit
    )
  ) %>%
  select(-matched_val)

方案2：纯data.table实现 #

library(data.table)
library(stringr)

# 构建匹配映射字典
match_dict <- data.table(
  pattern = c(vector_of_units_in, vector_of_units_euro),
  output = c(vector_of_units_out, rep(vector_of_units_euro_out, length(vector_of_units_euro)))
)

# 生成正则表达式
match_regex <- paste0(match_dict$pattern, collapse = "|")

# 步骤1：提取匹配的原始值
example_dat[, matched_val := str_extract(description, match_regex)]

# 步骤2：根据映射替换，无匹配则保留原有unit值
example_dat[, unit := fifelse(!is.na(matched_val), match_dict$output[match(matched_val, match_dict$pattern)], unit)]

# 可选：删除中间辅助列
example_dat[, matched_val := NULL]

关键说明 #

• 映射字典可清晰管理匹配规则，便于后续扩展新的匹配项
• 使用match()函数实现原始匹配值到目标输出的精准映射，避免手动编写大量条件
• fifelse()（data.table）或case_when()（dplyr）确保无匹配时保留原有值，不会被<NA>覆盖
• 如需调整匹配优先级，只需修改映射字典中pattern的顺序（正则匹配会优先匹配先出现的模式）

内容的提问来源于stack exchange，提问作者Tom