如何重命名 R 中不同数据框中不同列中的观察值？

Question

I want to add "Name" to the start and "plc" to the end of the names of the observations in different columns in different dataframes, except where the names already have "Name" or "plc" in the right place. The following is a simple reprex.

Original dataframes

names1a <- c("Name Alperton plc", "Bury", "Central", "Durham")
names1b <- c("Egham plc", "Fulton", "Great", "Heywood plc")
year1 <- c(1999, 2000, 2001, 2001)
df1 <- data.frame(names1a, names1b, year1)

names2 <- c("Charleton plc", "Birmingham", "Name Tees", "Salford")
year2 <- c(2000, 1955, 2001, 2001)
df2 <- data.frame(names2, year2)

Desired result:

df1

            names1a          names1b year1
1 Name Alperton plc   Name Egham plc  1999
2     Name Bury plc  Name Fulton plc  2000
3  Name Central plc   Name Great plc  2001
4   Name Durham plc Name Heywood plc  2001

df2

               names2 year2
1  Name Charleton plc  2000
2 Name Birmingham plc  1955
3       Name Tees plc  2001
4    Name Salford plc  2001

My approach: I get the result I want, but I have a large dataset with many columns, so my approach is just too repetitive. I struggle with making functions and I think one would be useful here:

df1$names1a <- sub("$", " plc", df1$names1a)
df1$names1b <- sub("$", " plc", df1$names1b)
df2$names2 <- sub("$", " plc", df2$names2)
df1$names1a <- sub("plc plc", "plc", df1$names1a)
df1$names1b <- sub("plc plc", "plc", df1$names1b)
df2$names2 <- sub("plc plc", "plc", df2$names2)

df1$names1a <- sub("^", "Name ", df1$names1a)
df1$names1b <- sub("^", "Name ", df1$names1b)
df2$names2 <- sub("^", "Name ", df2$names2)
df1$names1a <- sub("Name Name", "Name", df1$names1a)
df1$names1b <- sub("Name Name", "Name", df1$names1b)
df2$names2 <- sub("Name Name", "Name", df2$names2)

Answer 1

The easiest would probably be to delete "Name" and "plc" and add it to everything afterwards, like so:

f <- function(x) paste("Name", trimws(gsub("^Name|plc$", "", x)), "plc")

cols <- c("names1a", "names1b")
df1[cols] <- lapply(df1[cols], f)
df1
#          names1a         names1b year1
# 1 Name Arton plc    Name Egh plc  1999
# 2  Name Bury plc  Name Futon plc  2000
# 3  Name Cntr plc    Name Grt plc  2001
# 4  Name Durh plc Name Hywood plc  2001

df2$names2 <- f(df2$names2)
df2
#             names2 year2
# 1  Name Chrton plc  2000
# 2 Name Biringh plc  1955
# 3      Name Ts plc  2001
# 4   Name Sford plc  2001

Answer 2

You could try this function which allows editing both data frames separately and can cope with any number of columns starting with "names...". Based on tidyverse packages:

library(dplyr)
library(stringr)

  fun <- function(df){
    df <-
      df %>% 
      mutate(across(starts_with("names"), ~ str_replace_all(., "^Name | plc$", "")),
             across(starts_with("names"), ~ paste("Name", .,  "plc")))
    return(df)
  }
  
fun(df = df1)
#>             names1a          names1b year1
#> 1 Name Alperton plc   Name Egham plc  1999
#> 2     Name Bury plc  Name Fulton plc  2000
#> 3  Name Central plc   Name Great plc  2001
#> 4   Name Durham plc Name Heywood plc  2001
  
fun(df2)
#>                names2 year2
#> 1  Name Charleton plc  2000
#> 2 Name Birmingham plc  1955
#> 3       Name Tees plc  2001
#> 4    Name Salford plc  2001

You could combine the two mutate functions into one:

mutate(across(starts_with("names"), ~ paste("Name", str_replace_all(., "^Name | plc$", ""), "plc")))

^{Created on 2021-01-17 by the reprex package (v0.3.0)}

Answer 3

You can just remove the confounding strings from the names first and then append 'name' and 'plc' however you like:

library(tidyverse)

names1a <- c("Name Alperton plc", "Bury", "Central", "Durham")

names1a <- str_replace_all(names1a, "Name ", "")
names1a <- str_replace_all(names1a, " plc", "")
names1a <- paste0("Name ", names1a, " plc")

names1a
#> [1] "Name Alperton plc" "Name Bury plc"     "Name Central plc" 
#> [4] "Name Durham plc"

^{Created on 2021-01-17 by the reprex package (v0.3.0)}