r - 在 R 中使用 ifelse 和 grepl 进行变异并创建具有匹配字符串的新列

Question

我正在尝试使用 grepl(部分匹配)和 ifelse 使用 mutate 创建新列。我有带单位的药物名称列表，我想用这些单位创建新列。这是我的药物名称示例，

 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

这是我试过的代码，

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))

当前输出是这样的，

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

我不想要 TRUE/FALSE 中的单位，而是应该指定确切的单位，像这样，

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

我正在尝试重新编码，但不知道该怎么做。此外，我需要将药物名称 (4MG/5ML) 中的指标提取到单独的列中。我可以在另一个查询中执行此操作，但需要使用 unit 进行单个查询。不是所有的药物都有这种格式，有些像这样 --> 01.MG-100MG，250MCG。

            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

谁能帮我解决这个问题？

Answer 1

这是使用 dplyr 和 purrr 的一种方法。

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，演练和概念验证:

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"

我使用 .*“获取所有后续信息”以找到单位的数量。这有时会得到比我们想要的更多的信息，但为了在一个单元之后找到所有类似值的词，我们需要全部抓取然后过滤。

我们需要防范 character(0) 并理想地转换为向量，所以

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

尽管您可能更喜欢使用空字符串 "" 而不是 NA_character_。

要进行过滤，这里有一个快速函数，可以在以下每个“单词”中查找任何数字。它还允许单独的 "-"，但如果它是最后一个匹配项，则将其删除。

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)
}

快速获得原始单位，始终是第一个词。

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"

好的，现在将其放入管道中:

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