基于来自其他列的特定字符的新数据集列（在 R 中）

Question

in my dataset I want to create a new column that will be conditional on characters from other two columns. If longDesciptions.desc.en_US has a word Plage in it AND at the same time externalCode starts with number 1 then add value A in a new column. If longDesciptions.desc.en_US does not have a word Plage in it AND at the same time externalCode starts with number 1 then add value B in a new column. Otherwise, leave it empty or NA.

df <- structure(list(X.OPERATOR. = c(" Clear and Delete", NA, NA, NA, 
NA, "<p>Je voornaamste taken:</p>"), externalCode = c("Job Profile.GUID", 
"1008141", "1008168", "1008170", "1008170", NA), longDesciptions.sectionId = c("sectionId", 
"199624017", "200226564", "200226592", "200226594", NA), longDesciptions.sectionType = c("sectionType", 
"LONGDESCRIPTION", "LONGDESCRIPTION", "LONGDESCRIPTION", "LONGDESCRIPTION", 
NA), longDesciptions.desc.en_US = c("US English", "Class: 06, Plage: C, Function code:", 
"Class: 03", "Class: 03", "<p>Als Legal Counsel maak je deel uit van het departement Secretariaat-Generaal. Je ondersteunt zowel de secretaris-generaal en de directie alsook de verschillende entiteiten van Elia groep, zowel op nationaal als internationaal niveau.</p>", 
NA), longDesciptions.desc.defaultValue = c("Default Value", "Class: 06, Plage: C, Function code:", 
"Class: 03", "Class: 03", NA, NA), longDesciptions.desc.en_GB = c("English (United Kingdom)", 
"Class: 06, Plage: C, Function code:", "Class: 03", "Class: 03", 
NA, NA), longDesciptions.desc.de_DE = c("German (Germany)", NA, 
NA, NA, NA, NA), longDesciptions.desc.fr_FR = c("French (France)", 
"Classe: 06, Plage: C, Code de la fonction:", "Classe: 03", "Classe: 03", 
NA, NA), longDesciptions.desc.nl_NL = c("Dutch (Netherlands)", 
"Klasse: 06, Plage: C, Functiecode:", "Klasse: 03", "Klasse: 03", 
NA, NA), longDesciptions.status = c("status(Valid Values : A/I   A for Active  I for Inactive  )", 
"A", "A", "A", NA, NA), longDesciptions.externalCode = c("externalCode", 
"1035137", "1035330", "1035330", NA, NA), longDesciptions.subModule = c("subModule", 
NA, NA, NA, NA, NA), NA. = c(NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_), NA..1 = c(NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_
), NA..2 = c(NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_), NA..3 = c(NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_), 
    NA..4 = c(NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_), NA..5 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..6 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..7 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..8 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..9 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..10 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..11 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..12 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..13 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..14 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..15 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..16 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..17 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..18 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..19 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..20 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..21 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..22 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..23 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..24 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..25 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..26 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..27 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..28 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..29 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..30 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..31 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    ), NA..32 = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), NA..33 = c(NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_, 
    NA_character_), NA..34 = c(NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_, NA_character_
    )), class = "data.frame", row.names = c(NA, -6L))

I have tried this code but it does not work:

df2[,49] <- NA #
names(df2)[49] <- "JobDescrip" 

for (i in 1 : nrow(df2)) {
  if (df2$externalCode[i] == '^1' && df2$longDesciptions.sectionId[i]==
      '^P') {
    df2[i,49] <- "A"
  } 
  if (df2$externalCode[i] == '^1') {
    df2[i,49] <- "B"
  } 
  else {
    df2[i,49] <- ""
  }
}

Error in if (df2$externalCode[i] == "^1" && df2$longDesciptions.sectionId[i] ==  : 
  missing value where TRUE/FALSE needed

I know that this type of a question has been asked many times but I could not find a solution feasible for my data. Any help would be appreciated!

Answer 1

Here is a tidyverse approach you could consider. I would think about other vectorized approaches instead of a loop.

In this case, you can use mutate from dplyr to add your new column, and case_when instead of multiple if statements to add logic. If the first evaluation is false, then the second evaluation is tested, and so on.

If you use grepl you can check if the string contains "Plage" (you can consider alternatives for other regex patterns). Use of substr can look at specific characters in a string.

library(dplyr)

df %>%
  mutate(job_descrip = case_when(
    grepl("Plage", longDesciptions.desc.en_US) & substr(externalCode, 1, 1) == "1" ~ "A",
    substr(externalCode, 1, 1) == "1" ~ "B",
    TRUE ~ NA_character_
  ))