Question

如何扩展＆＃34; Coderange＆＃34;中的值？柱？我的数据有两列：CodeRange和Desc。我想在数据框中添加第三列，其中包含codeRange列中矢量的各个值。我如何在R？中做到这一点？

这就是我现在的表格

CodeRange  Desc   
61000:61055 Test1 
61000:61055 Test1 
61000:61055 Test1
0356T:0358T Test2  
S9090:S9090 Test3 
0062T:0062T Test4

这是我希望的最终结果

CodeRange  Desc   Codes(new Column to be add)
61000:61055 Test1 61001
61000:61055 Test1 61002
61000:61055 Test1 61003
61000:61055 Test1 61004
61000:61055 Test1 61005
  .
  .
61000:61055 Test1 61055
0356T:0358T Test2 0356T
0356T:0358T Test2 0357T
0356T:0358T Test2 0358T
S9090:S9090 Test3 S9090
0062T:0062T Test4 0062T

Answer 1

dt <- read.table(text = "CodeRange  Desc   
61000:61055 Test1 
61000:61055 Test1 
61000:61055 Test1
0356T:0358T Test2  
S9090:S9090 Test3 
0062T:0062T Test4 
", stringsAsFactors = FALSE, header = TRUE)

dt <- dt[!duplicated(paste(dt$CodeRange, dt$Desc)),]

expand_code <- function(x){
  code_range <- x[1]

  code_range_raw  <- as.character(unlist(strsplit(code_range, ":")))
  letters     <- stringr::str_extract(code_range, "[^0-9]")
  letters_pos <- stringr::str_locate(code_range, "[^0-9]")

  code_range <- gsub("[^0-9]", "", code_range_raw)
  code_range <- seq(from = code_range[1], to = code_range[2], by = 1)

  if(nchar(code_range_raw[1]) != nchar(code_range[1])){
    code_range <- paste0(strrep("0", 
                nchar(code_range_raw[1]) - nchar(code_range[1]) - nchar(letters[1])), 
                code_range)
  }

  if(letters_pos[[1]] == nchar(code_range_raw[1])){
      code_range <- paste0(code_range, letters[1])
  }
  if(letters_pos[[1]] < nchar(code_range_raw[1])){
      code_range <- paste0(letters[1], code_range)
  }


  data.frame(CodeRange = x[1], Desc = x[2], Code = code_range, row.names = NULL)
}

do.call("rbind", apply(dt, 1, expand_code))

Answer 2

df=df[!duplicated(df),] 
values=sapply(parse(text=gsub("[A-Za-z]+","",df$CodeRange)),eval)#EXPAND
dat=`row.names<-`(df[rep(1:nrow(df),lengths(values)),],NULL)#MAKE THE NEW LARGE DF
Codes=sub(":.*","",dat$CodeRange)
regmatches(Codes,regexpr("\\d+",Codes))<-sprintf("%04.0f", unlist(values))#INCLUDE THE LETTERS TO THE LARGE DF
dat$Codes=Codes

head(dat)
    CodeRange  Desc Codes
1 61000:61055 Test1 61000
2 61000:61055 Test1 61001
3 61000:61055 Test1 61002
4 61000:61055 Test1 61003
5 61000:61055 Test1 61004
6 61000:61055 Test1 61005
  tail(dat)
     CodeRange  Desc Codes
56 61000:61055 Test1 61055
57 0356T:0358T Test2 0356T
58 0356T:0358T Test2 0357T
59 0356T:0358T Test2 0358T
60 S9090:S9090 Test3 S9090
61 0062T:0062T Test4 0062T

一个问题是重复data 1:3。那么你想使用df=df[!duplicated(df),]然后执行上面的

DATA：

df=read.table(text="CodeRange  Desc   
61000:61055 Test1 
               61000:61055 Test1 
               61000:61055 Test1
               0356T:0358T Test2  
               S9090:S9090 Test3 
               0062T:0062T Test4 ",h=T,stringsAsFactors=F)

如何在列中展开矢量类型值

2 个答案: