R语言双循环报错：需用.name_repair修复空列名问题

问题背景 #

用户拥有如下R语言数据集：

set.seed(123)

myFun <- function(n = 5000) {
  a <- do.call(paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
  paste0(a, sprintf("%04d", sample(9999, n, TRUE)), sample(LETTERS, n, TRUE))
}

col1 = myFun(100)
col2 = myFun(100)
col3 = myFun(100)
col4 = myFun(100)
group <- c("A","B","C","D")
group = sample(group, 100, replace=TRUE)

example = data.frame(col1, col2, col3, col4, group)

原单循环代码可计算全量数据的字符串距离指标，改为按group分组计算的双循环代码后，出现如下错误：

Error:
! Column 1 must be named.
Use .name_repair to specify repair.
Caused by error in `repaired_names()`:
! Names can't be empty.
x Empty name found at location 1.

用户编写的错误双循环代码：

results = list()


for (i in 1:length(method))
for (j in 1:length(unique(example$group))

{

{

groups_j = unique(example$group[j])
my_data_i = file[which(file$fsa == groups_j  ), ]


method_i = method[i]
name_1_i = paste0("col1_col_2", method_i)
 name_2_i = paste0("col3_col_4", method_i)

p1_i = stringdistmatrix(my_data_i$col1, my_data_i$col2, method =  method_i, useNames = "string") %>%
            as_tibble(rownames = "a") %>%
            pivot_longer(-1, names_to = "b", values_to = name_1_i)

p2_i = stringdistmatrix(my_data_i$col3, my_data_i$col4, method =  method_i, useNames = "string") %>%
            as_tibble(rownames = "a") %>%
            pivot_longer(-1, names_to = "b", values_to = name_2_i)

p1_i = p1_i[,3]
p2_i = p2_i[,3]

final_i = cbind(p1_i, p2_i)
 results[[i]] = final_i

}
   
}

final = do.call(cbind.data.frame, results)
final = cbind(col1,col2, col3,col4, final)

average_col1_col2_dist = (final$col1_col_2osa  + final$col1_col_2lv + final$col1_col_2dl      + final$col1_col_2hamming + final$col1_col_2lcs +     final$col1_col_2qgram  + final$col1_col_2cosine    + final$col1_col_2jaccard + final$col1_col_2jw   + final$col1_col_2soundex)/10

 average_col3_col4_dist =  ( final$col3_col_4osa     +    final$col3_col_4lv       +     final$col3_col_4dl  +     final$col3_col_4hamming +  final$col3_col_4lcs +  final$col3_col_4qgram  +   final$col3_col_4cosine +    final$col3_col_4jaccard  +    final$col3_col_4jw     +   final$col3_col_4soundex)/10

final = data.frame( col1, col2, col3, col4, average_col1_col2_dist,  average_col3_col4_dist)
final = scale(final)

错误原因分析 #

• 循环语法缺失：第二个for循环末尾未加闭合括号，导致代码结构混乱。
• 变量引用错误：使用了不存在的file对象（应为example），且错误引用fsa列（实际是group列）。
• 分组提取逻辑错误：unique(example$group[j])无法正确获取分组，应该直接遍历唯一分组值而非索引。
• 结果存储覆盖：双循环中仅用results[[i]]存储，会覆盖同一方法下不同分组的结果，导致数据结构异常。
• 列名丢失问题：p1_i = p1_i[,3]这类操作会移除列名，后续合并时出现空列名触发报错。

修复后的完整代码 #

library(stringdist)
library(tidyverse)

method = c("osa", "lv", "dl", "hamming", "lcs", "qgram", "cosine", "jaccard", "jw","soundex")

# 初始化结果列表，按"分组_方法"命名存储
results <- list()

# 获取所有唯一分组
unique_groups <- unique(example$group)

# 双循环：外层遍历分组，内层遍历距离计算方法
for (j in seq_along(unique_groups)) {
  current_group <- unique_groups[j]
  # 提取当前分组的数据集
  group_data <- example %>% filter(group == current_group)
  
  for (i in seq_along(method)) {
    current_method <- method[i]
    # 定义列名，避免格式混乱
    col1_col2_name <- paste0("col1_col2_", current_method)
    col3_col4_name <- paste0("col3_col4_", current_method)
    
    # 计算col1与col2的字符串距离矩阵，整理为长格式
    dist_col1_col2 <- stringdistmatrix(group_data$col1, group_data$col2, method = current_method, useNames = "string") %>%
      as_tibble(rownames = "col1_val") %>%
      pivot_longer(-col1_val, names_to = "col2_val", values_to = col1_col2_name)
    
    # 计算col3与col4的字符串距离矩阵，整理为长格式
    dist_col3_col4 <- stringdistmatrix(group_data$col3, group_data$col4, method = current_method, useNames = "string") %>%
      as_tibble(rownames = "col3_val") %>%
      pivot_longer(-col3_val, names_to = "col4_val", values_to = col3_col4_name)
    
    # 合并当前方法的结果，添加分组标识
    combined_data <- bind_cols(dist_col1_col2, dist_col3_col4) %>% mutate(group = current_group)
    # 按"分组_方法"命名存储到列表
    results[[paste0(current_group, "_", current_method)]] <- combined_data
  }
}

# 合并所有分组+方法的结果
full_results <- bind_rows(results)

# 计算每组内的平均距离
average_results <- full_results %>%
  group_by(group, col1_val, col2_val, col3_val, col4_val) %>%
  summarise(
    average_col1_col2_dist = mean(c_across(starts_with("col1_col2_"))),
    average_col3_col4_dist = mean(c_across(starts_with("col3_col4_"))),
    .groups = "drop"
  )

# 仅对数值型的平均距离列做标准化处理
scaled_results <- average_results %>%
  mutate(across(c(average_col1_col2_dist, average_col3_col4_dist), scale))

关键修复说明 #

• 修正循环结构：补全循环括号，调整为外层遍历分组、内层遍历方法的逻辑，契合分组计算需求。
• 修复变量引用：将file改为example，fsa改为group，确保数据提取正确。
• 保留列名完整性：移除p1_i = p1_i[,3]这类丢失列名的操作，后续通过starts_with精准匹配列进行均值计算。
• 避免数据覆盖：用分组_方法作为列表元素名称，确保不同分组的结果独立存储，最后通过bind_rows合并。
• 规范均值计算：使用c_across+mean替代手动求和除以10，代码更简洁且不易出错。
• 正确标准化：仅对数值型的平均距离列执行scale操作，避免对字符串列做无效处理。

内容的提问来源于stack exchange，提问作者stats_noob