在R中使用ifelse和grepl进行变异，并使用匹配的字符串创建新列

Question

我试图用grepl（部分匹配）和ifelse使用mutate创建新列。我有单位的药物名称列表，我想用这些单位创建新的列。这是我的药名样本，

 Description
    ZOLEDRONIC ACID INF 4MG/5ML (5ML)
    CALCICHEW D3 FORTE CHEWABLE TABS
    DAYCASE DRUGS
    AKYNZEO (NETUPITANT/PALONOSETRON) HARD CAPS 300MG/0.5MG
    CYCLOPHOSPHAMIDE INF 1MG/ML
    EPIRUBICIN INJ 1MG/ML
    DAYCASE DRUGS
    DAYCASE DRUGS
    ALOXI (PALONOSETRON) INJ 250MCG
    PACLITAXEL INF 1MG/ML
    DEXAMETHASONE VIAL 6.6MG/2ML - USE PSD742
    PACLITAXEL INF 1MG/ML
    RAMUCIRUMAB INF 0.1MG - 100MG

units <- c("TABS","INF","SYR","CAPS","INJ","VIAL","SOL","POWDER","GEL","CREAM","LOTION","AMP"," SINGLEJECT","PFS")

drug_name <- drug_name %>% mutate(unit =  grepl(paste(units,collapse = "|"),Description))

Description                                 unit
ZOLEDRONIC ACID INF 4MG/5ML (5ML)           TRUE
    CALCICHEW D3 FORTE CHEWABLE TABS        TRUE
    DAYCASE DRUGS                           FALSE
    AKYNZEO (NETUPITANT/PALONOSETRON) CAPS  TRUE
    CYCLOPHOSPHAMIDE INF 1MG/ML             TRUE
    EPIRUBICIN INJ 1MG/ML                   TRUE
    DAYCASE DRUGS                           FALSE
    DAYCASE DRUGS                           FALSE

        ZOLEDRONIC ACID INF 4MG/5ML (5ML)       INF
        CALCICHEW D3 FORTE CHEWABLE TABS        TABS

            ZOLEDRONIC ACID INF 4MG/5ML (5ML)       INF    4MG/5ML
            CALCICHEW D3 FORTE CHEWABLE TABS        TABS   NA
            CYCLOPHOSPHAMIDE INF 1MG/ML             INF    1MG/ML
            ALOXI (PALONOSETRON) INJ 250MCG         INF    250MCG

Answer 1

下面是一个使用dplyr和purrr的方法。

library(dplyr)
library(purrr)
drug_name <- data_frame(
  Description = trimws(readLines(textConnection('ZOLEDRONIC ACID INF 4MG/5ML (5ML)
    CALCICHEW D3 FORTE CHEWABLE TABS
    DAYCASE DRUGS
    AKYNZEO (NETUPITANT/PALONOSETRON) HARD CAPS 300MG/0.5MG
    CYCLOPHOSPHAMIDE INF 1MG/ML
    EPIRUBICIN INJ 1MG/ML
    DAYCASE DRUGS
    DAYCASE DRUGS
    ALOXI (PALONOSETRON) INJ 250MCG
    PACLITAXEL INF 1MG/ML
    DEXAMETHASONE VIAL 6.6MG/2ML - USE PSD742
    PACLITAXEL INF 1MG/ML
    RAMUCIRUMAB INF 0.1MG - 100MG')))
)
units <- c("TABS","INF","SYR","CAPS","INJ","VIAL","SOL","POWDER",
           "GEL","CREAM","LOTION","AMP","SINGLEJECT","PFS")
units1 <- sprintf("\\b(%s)\\b", paste(units, collapse = "|"))

首先，一个简单的概念验证：

m <- regmatches(drug_name$Description,
                gregexpr(paste0(units1, ".*"), drug_name$Description))
m
# [[1]]
# [1] "INF 4MG/5ML (5ML)"
# [[2]]
# [1] "TABS"
# [[3]]
# character(0)
# [[4]]
# [1] "CAPS 300MG/0.5MG"
# [[5]]
# [1] "INF 1MG/ML"
# [[6]]
# [1] "INJ 1MG/ML"
# [[7]]
# character(0)
# [[8]]
# character(0)
# [[9]]
# [1] "INJ 250MCG"
# [[10]]
# [1] "INF 1MG/ML"
# [[11]]
# [1] "VIAL 6.6MG/2ML - USE PSD742"
# [[12]]
# [1] "INF 1MG/ML"
# [[13]]
# [1] "INF 0.1MG - 100MG"

我用.*“获取所有以下内容”，以便找到单位的数量。这有时会得到比我们想要的更多的东西，但是为了在一个单位后面找到所有类似值的单词，我们需要抓取所有的单词，然后进行过滤。

fixEmpties <- function(lst, default=NA_character_)
  unlist(replace(lst, lengths(lst) == 0L, default))

extractAmounts <- function(s, default=NA_character_) {
  vec <- strsplit(s, "\\s+")[[1]][-1]
  vec2 <- which(cumall(grepl("[0-9]", vec) | vec == "-"))
  if (isTRUE(length(vec2) > 0)) {
    # remove a trailing "-" that does not result in a range
    if (vec[ tail(vec2, 1) ] == "-") vec2 <- vec2[-length(vec2)]
    return(paste(vec[vec2], collapse = " "))
  } else return(default)
}

extractUnits <- function(s)
  head(strsplit(s, "\\s+")[[1]], 1)

测试：

m <- fixEmpties(m)
sapply(m, extractUnits, USE.NAMES=FALSE)
#  [1] "INF"  "TABS" NA     "CAPS" "INF"  "INJ"  NA     NA     "INJ"  "INF" 
# [11] "VIAL" "INF"  "INF" 
sapply(m, extractAmounts, USE.NAMES=FALSE)
#  [1] "4MG/5ML (5ML)" NA              NA              "300MG/0.5MG"  
#  [5] "1MG/ML"        "1MG/ML"        NA              NA             
#  [9] "250MCG"        "1MG/ML"        "6.6MG/2ML"     "1MG/ML"       
# [13] "0.1MG - 100MG"

好了，现在把这个放进管子里：

drug_name %>%
  mutate(
    full = fixEmpties(regmatches(Description, gregexpr(paste0(units1, ".*"), Description))),
    unit = map_chr(full, extractUnits),
    amt = map_chr(full, extractAmounts)
  ) %>%
  select(-full)
# # A tibble: 13 x 3
#    Description                                             unit  amt          
#    <chr>                                                   <chr> <chr>        
#  1 ZOLEDRONIC ACID INF 4MG/5ML (5ML)                       INF   4MG/5ML (5ML)
#  2 CALCICHEW D3 FORTE CHEWABLE TABS                        TABS  <NA>         
#  3 DAYCASE DRUGS                                           <NA>  <NA>         
#  4 AKYNZEO (NETUPITANT/PALONOSETRON) HARD CAPS 300MG/0.5MG CAPS  300MG/0.5MG  
#  5 CYCLOPHOSPHAMIDE INF 1MG/ML                             INF   1MG/ML       
#  6 EPIRUBICIN INJ 1MG/ML                                   INJ   1MG/ML       
#  7 DAYCASE DRUGS                                           <NA>  <NA>         
#  8 DAYCASE DRUGS                                           <NA>  <NA>         
#  9 ALOXI (PALONOSETRON) INJ 250MCG                         INJ   250MCG       
# 10 PACLITAXEL INF 1MG/ML                                   INF   1MG/ML       
# 11 DEXAMETHASONE VIAL 6.6MG/2ML - USE PSD742               VIAL  6.6MG/2ML    
# 12 PACLITAXEL INF 1MG/ML                                   INF   1MG/ML       
# 13 RAMUCIRUMAB INF 0.1MG - 100MG                           INF   0.1MG - 100MG