如何在R语言中为循环迭代的DataFrame列名添加迭代计数？

问题说明 #

第一次用R写for循环，想给循环里生成的concat、alloc、merge、reSeq列名加上循环迭代编号——比如第一次循环后变成concat_1、alloc_1、merge_1、reSeq_1，第二次循环变成concat_2以此类推。之前试过在mutate里直接写mutate(paste0("concat_",i) = as.numeric...)，但根本不生效，想知道正确的处理方式。

解决方法 #

dplyr的mutate不支持直接用字符串作为列名赋值，得用动态列名语法，下面给两种可行方案：

方案1：生成列时直接用动态命名（推荐）

用:=操作符结合!!（非标准求值）来绑定动态生成的列名，同时用.data或all_of()引用这些动态列名，代码修改如下：

library(dplyr)

myDF1 <- data.frame(
    Name = c("R","R","B","R","X","X"),
    Group = c(0,0,0,0,1,1))

nCode <-  myDF1 %>%
  group_by(Name) %>%
  mutate(nmCnt = row_number()) %>%
  ungroup() %>%
  mutate(seqBase = ifelse(Group == 0 | Group != lag(Group), nmCnt,0)) %>%
  mutate(seqBase = na_if(seqBase, 0)) %>%
  group_by(Name) %>%
  fill(seqBase) %>%
  mutate(seqBase = match(seqBase, unique(seqBase))) %>%
  ungroup %>%
  mutate(grpRnk = ifelse(Group > 0, sapply(1:n(), function(x) sum(Name[1:x]==Name[x] & Group[1:x] == Group[x])),0))
    
loopCntr <- nrow(unique(myDF1[myDF1$Group!=0,]))

for(i in 1:loopCntr) {
  # 先定义带迭代号的列名
  concat_col <- paste0("concat_", i)
  alloc_col <- paste0("alloc_", i)
  merge_col <- paste0("merge_", i)
  reSeq_col <- paste0("reSeq_", i)
  
  # 用!!和:=动态创建concat列
  nCode <- nCode %>% 
    mutate(!!concat_col := as.numeric(paste0(seqBase,".",grpRnk)))
  
  index <- filter(nCode, Group !=0) %>% 
    select(all_of(concat_col)) %>% # 用all_of引用动态列名
    distinct() %>% 
    mutate(truncInd = trunc(.data[[concat_col]])) %>% # .data[[列名]]引用动态列
    group_by(truncInd) %>% 
    mutate(cumGrp = cur_group_id()) %>%
    ungroup() %>%
    select(-truncInd)
  
  index <- if(ifelse(loopCntr > 0, min(index[[concat_col]]), Inf) >= 2){
    rbind(data.frame(!!concat_col := c(1), cumGrp=c(1)), index)}else{index}
  
  # 同理处理其他列的动态命名
  nCode <- nCode %>%
    mutate(!!alloc_col := index[[concat_col]][index$cumGrp==1][nmCnt]) %>%
    mutate(!!merge_col := ifelse(is.na(.data[[alloc_col]]), seqBase, .data[[alloc_col]])) %>%
    group_by(Name) %>%
    mutate(!!reSeq_col := match(trunc(.data[[merge_col]]), unique(trunc(.data[[merge_col]])))) %>%
    mutate(!!reSeq_col := (.data[[reSeq_col]] + round(.data[[merge_col]]%%1 * 10,0)/10)) %>%
    ungroup()
}

print.data.frame(nCode)

关键要点：

• !!会把字符串格式的列名转换成dplyr能识别的符号，:=用来完成动态列的赋值
• 引用动态列时，用.data[[col_name]]（兼容所有dplyr版本）或all_of(col_name)（dplyr 1.0+推荐），避免列名识别错误

方案2：循环结束后批量重命名列

如果不想修改循环内的mutate逻辑，可以在每次循环末尾，找到刚生成的concat、alloc、merge、reSeq列，替换成带迭代号的名称：

library(dplyr)

myDF1 <- data.frame(
    Name = c("R","R","B","R","X","X"),
    Group = c(0,0,0,0,1,1))

nCode <-  myDF1 %>%
  group_by(Name) %>%
  mutate(nmCnt = row_number()) %>%
  ungroup() %>%
  mutate(seqBase = ifelse(Group == 0 | Group != lag(Group), nmCnt,0)) %>%
  mutate(seqBase = na_if(seqBase, 0)) %>%
  group_by(Name) %>%
  fill(seqBase) %>%
  mutate(seqBase = match(seqBase, unique(seqBase))) %>%
  ungroup %>%
  mutate(grpRnk = ifelse(Group > 0, sapply(1:n(), function(x) sum(Name[1:x]==Name[x] & Group[1:x] == Group[x])),0))
    
loopCntr <- nrow(unique(myDF1[myDF1$Group!=0,]))

for(i in 1:loopCntr) {
  # 保留原循环逻辑，生成临时列名concat/alloc等
  nCode <- nCode %>% 
    mutate(concat = as.numeric(paste0(seqBase,".",grpRnk)))
  
  index <- filter(nCode, Group !=0) %>% 
    select(concat) %>% 
    distinct() %>% 
    mutate(truncInd = trunc(concat)) %>%
    group_by(truncInd) %>% 
    mutate(cumGrp = cur_group_id()) %>%
    ungroup() %>%
    select(-truncInd)
  
  index <- if(ifelse(loopCntr > 0, min(index$concat), Inf) >= 2){
    rbind(data.frame(concat=c(1),cumGrp=c(1)),index)}else{index}
  
  nCode <- nCode %>%
    mutate(alloc = index$concat[index$cumGrp==1][nmCnt]) %>%
    mutate(merge = ifelse(is.na(alloc),seqBase,alloc)) %>%
    group_by(Name) %>%
    mutate(reSeq = match(trunc(merge), unique(trunc(merge)))) %>%
    mutate(reSeq = (reSeq + round(merge%%1 * 10,0)/10)) %>%
    ungroup()
  
  # 循环末尾重命名刚生成的4列
  target_cols <- c("concat", "alloc", "merge", "reSeq")
  new_names <- paste0(target_cols, "_", i)
  colnames(nCode)[match(target_cols, colnames(nCode))] <- new_names
}

print.data.frame(nCode)

注意：这个方法依赖match找到最新生成的临时列，适合每次循环只生成一组临时列的场景。

内容的提问来源于stack exchange，提问作者Village.Idyot