如何使用其他列中的数据填充列中的所有行？

Question

我有一个名为'names'的数据集，如下所示。 'expected.entry.in.this.col'列目前是空的，但下面我已经展示了它应该是什么样子。我该如何编写逻辑？

基本上我认为我需要在每一行和每一行中运行循环，使用'if'条件检查格式，然后适当地将数据输入'expected.entry.in.this.col' 。我该怎么做呢？ （对这些任务有点不熟悉R语法）。

名称

编辑：第3行是一个错误，应该阅读williams.harry

Answer 1

尝试这样的事情：

df <- data.frame(first = c("Kevin", "Megan"), last = c("Spacey", "Fox"),
                 format = c("f.last", "F.L."))

df$new <- NA
df$new <- ifelse(df$format == "f.last",
                 tolower(paste0(substr(df$first,1,1),".",df$last)),
                 df$new)
df$new <- ifelse(df$format == "F.L.",
                 paste0(substr(df$first,1,1),".", substr(df$last,1,1)),
                 df$new)

df

  first   last format      new
1 Kevin Spacey f.last k.spacey
2 Megan    Fox   F.L.      M.F

Answer 2

我是这样做的，我希望你能得到逻辑！告诉我这是否是你想要的

first = c('John','Michael',"Harry","Stephen","Simon",'Rachael',"Paul")
last = c("smith","Johnson","Williams","Jones","Adams","Moore","Taylor")
format = c("first.last","firstlast","last.first","f.last","flast","f_last","f_last")

names = data.frame(cbind(first,last,format))

names$first = as.character(names$first)
names$last = as.character(names$last)
names$format = as.character(names$format)

library(stringr)

for (i in 1:dim(names)[1]){
  if (names[i,"format"] == "first.last"){
    names[i,"new_var"] = paste(tolower(names[i,"first"]),tolower(names[i,"last"]), sep = '.')
  }else if (names[i,"format"] == "firstlast"){
    names[i,"new_var"]= paste(tolower(names[i,"first"]),tolower(names[i,"last"]), sep = '')
  }else if (names[i,"format"] == "last.first"){
    names[i,"new_var"] = paste(tolower(names[i,"last"]),tolower(names[i,"first"]), sep = '.')
  }else if (names[i,"format"] == "f.last"){
    names[i,"new_var"] = paste(tolower(str_sub(names[i,"first"],1,1)),tolower(names[i,"last"]),sep=".")
  }else if (names[i,"format"] == "flast"){
    names[i,"new_var"] = paste(tolower(str_sub(names[i,"first"],1,1)),tolower(names[i,"last"]),sep="")
  }else{
    names[i,"new_var"] = paste(tolower(str_sub(names[i,"first"],1,1)),tolower(names[i,"last"]),sep="_")
  }
}

names

    first     last     format        new_var
1    John    smith first.last     john.smith
2 Michael  Johnson  firstlast michaeljohnson
3   Harry Williams last.first williams.harry
4 Stephen    Jones     f.last        s.jones
5   Simon    Adams      flast         sadams
6 Rachael    Moore     f_last        r_moore
7    Paul   Taylor     f_last       p_taylor
> 

Answer 3

这是一个带有＆＃34;查找表的解决方案＆＃34;没有if＆＃39;

mydf <- data.frame(
  first= c("John", "Michael", "Harry", "Stephen", "Simon", "Rachael", "Paul"),
  last = c("Smith", "Johnson", "Williams", "Jones", "Adams", "Moore", "Taylor"),
  format = c("first.last", "firstlast", "last.first", "f.last", "flast", "f_last", "f_last"),
  expected = c("", "", "", "", "", "", ""),
  stringsAsFactors = FALSE
  )
library(dplyr)

firstList <- c("first.last", "firstlast", "f.last", "flast", "f_last")

#if in the format is in firstList, then do this
mydf[mydf$format %in% firstList, ]$expected <- paste0(
  mydf[mydf$format %in% firstList, ]$first, ".", 
  mydf[mydf$format %in% firstList, ]$last)

mydf[ !(mydf$format %in% firstList), ]$expected <- paste0(
  mydf[ !(mydf$format %in% firstList), ]$last, ".", 
  mydf[ !(mydf$format %in% firstList), ]$first)
)