R: текст здания Классификатор

Question

У меня есть набор контента, который должен быть классифицирован по нескольким правилам.

выборка данных:

1  chin jeffrey hong kong wednesday october  global business reporting cc subramanian raghuveer kumar m santhosh antoo ramesh subject request obtain global icis data dear team appreciate can distribute monthly basis latest global icis data ramesh antoo upon availability regards jeffrey chin associate business risk strategy efficiency brse asia international institutional banking australia new zealand banking group limited f three exchange square connaught place central hong kong phone voice net email jeffreychinanzcom brse key business risk interface team within iib providing global support strategic perspectives policy procedures reporting includes risk appetite credit process quality assurance interlock key stakeholders well iib support key projects project glue cacheorion working groups efficiency initiatives business risk forums p please consider environment printing email 
    2  beren stuart vanuatu monday october  g s venkatesh ramesh sandeep talanki h r nagaraj subject please approve qlikview gpa access hi please process following form gpa access please email requestor line manager access granted raj can please add given user qlikview workgroup gpa access form requestors name lim tek kon vanuatu address lini high way port vila efate title relationship manager emerging corporates employee id lan id limtk bsbcc authorising manager beren stuart vanuatu yes read use gpa dashboard business technical reason na 
    3  kumar m santhosh behalf relationshipbankingfinancesupport friday october  g s venkatesh cc global business reporting subject fw please approve qlikview gpa access regards santhosh faunt daniel png wednesday october  relationshipbankingfinancesupport cc amet sova subject fw please approve qlikview gpa access hi unable approve excel due macro issues please process amet sova monday october  faunt daniel png subject please approve qlikview gpa access hello can please review attached form click line manager approval approve 
    4  thomson owen tonga thursday october  g s venkatesh ramesh sandeep talanki h r nagaraj subject please approve qlikview gpa access hi please process following form gpa access please email requestor line manager access granted raj can please add given user qlikview workgroup gpa access form requestors name hia viliami address head office fakafanua centre maufanga vuna road nukualofa tongatapu tonga nukualofa tongatapu title nfc amu manager employee id lan id hiav bsbcc authorising manager thomson owen tonga yes read use gpa dashboard business technical reason 
    5  kumar rajesh fiji tuesday october  g s venkatesh ramesh sandeep talanki h r nagaraj subject please approve qlikview gpa access hi please process following form gpa access please email requestor line manager access granted raj can please add given user qlikview workgroup gpa access form requestors 

Это только одно значение строки, где в режиме реального времени я должен пройти через более чем 500 - 10000 строк, как, например, здесь я извлек слова, которые IL быть используя

> O 
$text 
$text[[1]] 
[1] "qlikview" "gpa"  "access" "gpa"  "access" "access" "qlikview" "gpa"  "access" "gpa"  

$text[[2]] 
[1] "report" "qlikview" "gpa"  "access" "qlikview" "gpa"  "access" "qlikview" "gpa"  
[10] "access" 

$text[[3]] 
[1] "qlikview" "gpa"  "access" "gpa"  "access" "access" "qlikview" "gpa"  "access" 
[10] "gpa"  

$text[[4]] 
[1] "qlikview" "gpa"  "access" "gpa"  "access" "access" "qlikview" "gpa"  "access" 
[10] "gpa"  

$text[[5]] 
[1] "report" "qlikview" "gpa"  "access" "access" "gpa"  "access" "qlikview" "gpa" "access" "access" "gpa"  "qlikview" "gpa"  "access" "qlikview" "gpa" "access" 

$text[[6]] 
[1] "report" "qlikview" "access" "access" "report" "qlikview" "access" "access" "gpa"  
[10] "qlikview" "access" "access" "qlikview" "access" "access" 

$text[[7]] 
[1] "report" "report" "access" "access" "report" "report" "report" "report" "report" "report" "data" "data" "report" "access" "report" "report" 

$text[[8]] 
[1] "report" "qlikview" "gpa"  "access" "gpa"  "access" 

$text[[9]] 
[1] "report" "gpa" "access" "access" "gpa" "gpa" "gpa" "gpa" "gpa" "access" "gpa" "gpa" "gpa" "report" 

$text[[10]] 
[1] "report" "gpa" "gpa" "access" "gpa" "access" "gpa" "access" "gpa" "gpa" "report" "gpa" "gpa" "access" "gpa" "gpa" "gpa" "gpa" "gpa" 

теперь я строить правило на это, используя, если условие в то время, как же список будет представлен в цикле для каждого текста и проверить, если «доступ» присутствует, то проверьте «GPA» или «QlikView» присутствует, а затем возвращается как ACCESS для значения строки (данные выборки) в еще, если «отчет» присутствует, то проверьте «ПФП» или «региональный» возвращение ОТЧЕТ

Я преобразовал приведенный выше список, как dataframe, который выглядит следующим

код:

maxl <- max(sapply(O,length)) 
out <- do.call(cbind, lapply(O,function(x) x[1:maxl])) 
out <- as.data.frame(out) 
    text 
1 c("qlikview", "gpa", "access", "gpa", "access", "access", "qlikview", "gpa", "access", "gpa") 
2 c("report", "qlikview", "gpa", "access", "qlikview", "gpa", "access", "qlikview", "gpa", "access") 
3 c("qlikview", "gpa", "access", "gpa", "access", "access", "qlikview", "gpa", "access", "gpa") 
4 c("qlikview", "gpa", "access", "gpa", "access", "access", "qlikview", "gpa", "access", "gpa") 
5 c("report", "qlikview", "gpa", "access", "access", "gpa", "access", "qlikview", "gpa", "access", "access", "gpa", "qlikview", "gpa", "access", "qlikview", "gpa", "access") 
6 c("report", "qlikview", "access", "access", "report", "qlikview", "access", "access", "gpa", "qlikview", "access", "access", "qlikview", "access", "access") 

как я могу удалить тип c() списка в этом dataframe?

попробовал код:

#Rule Classifier----- 
rule <- function(out) 
{ 
    for(i in out) 
    { 
    for(j in out[i]) 
    { 
     if(x[j]=="Access") 
     { 
     if(x[j]=="gpa" | x[j]=="qlikview") 
     { 
      return("Access") 
     } 
     } 
     else if(x[j]=="Report") 
     { 
     if(x[j]=="pfi" | x[j]=="data") 
     { 
      return("Report") 
     } 
     } 
    } 
    } 
} 

Ожидаемый результат:

1  Access 
2  Access 
3  Access 
4  Access 
5  Access 
6  Access 
7  Report/Data 
8  Access 
9  Access 
10  Access 
11  Report/Data 
12  Report/Data 
13  Report/Data 
14  Report/Data 

dput(O$text[1:10]) 

list(c("qlikview", "gpa", "access", "gpa", "access", "access", 
"qlikview", "gpa", "access", "gpa"), c("report", "qlikview", 
"gpa", "access", "qlikview", "gpa", "access", "qlikview", "gpa", 
"access"), c("qlikview", "gpa", "access", "gpa", "access", "access", 
"qlikview", "gpa", "access", "gpa"), c("qlikview", "gpa", "access", 
"gpa", "access", "access", "qlikview", "gpa", "access", "gpa" 
), c("report", "qlikview", "gpa", "access", "access", "gpa", 
"access", "qlikview", "gpa", "access", "access", "gpa", "qlikview", 
"gpa", "access", "qlikview", "gpa", "access"), c("report", "qlikview", 
"access", "access", "report", "qlikview", "access", "access", 
"gpa", "qlikview", "access", "access", "qlikview", "access", 
"access"), c("report", "report", "access", "access", "report", 
"report", "report", "report", "report", "report", "data", "data", 
"report", "access", "report", "report"), c("report", "qlikview", 
"gpa", "access", "gpa", "access"), c("report", "gpa", "access", 
"access", "gpa", "gpa", "gpa", "gpa", "gpa", "access", "gpa", 
"gpa", "gpa", "report"), c("report", "gpa", "gpa", "access", 
"gpa", "access", "gpa", "access", "gpa", "gpa", "report", "gpa", 
"gpa", "access", "gpa", "gpa", "gpa", "gpa", "gpa")) 
rule(out) 
#this is throwing some error - Error in `[.default`(out, i) : invalid subscript type 'list' 

Я знаю, что это довольно наивно, но им новичок в этом, пожалуйста, поправьте меня, если я буду неправильно некоторые где.

Answer 1

Вы, кажется, считаете, что петли for ... in будут итерировать с целым числом. Они просто перебирают объекты в списке, поэтому вы пытаетесь использовать i в качестве индекса, когда это список. Но ?lapply покажет вам лучший способ работы со списками.

text <- list(c("qlikview", "gpa", "access", "gpa", "access", "access", 
      "qlikview", "gpa", "access", "gpa"), 
      c("report", "qlikview", 
      "gpa", "access", "qlikview", "gpa", "access", "qlikview", "gpa", 
      "access"), 
      c("qlikview", "gpa", "access", "gpa", "access", "access", 
      "qlikview", "gpa", "access", "gpa"), 
      c("qlikview", "gpa", "access", 
      "gpa", "access", "access", "qlikview", "gpa", "access", "gpa"), 
      c("report", "qlikview", "gpa", "access", "access", "gpa", 
      "access", "qlikview", "gpa", "access", "access", "gpa", "qlikview", 
      "gpa", "access", "qlikview", "gpa", "access"), 
      c("report", "qlikview", 
      "access", "access", "report", "qlikview", "access", "access", 
      "gpa", "qlikview", "access", "access", "qlikview", "access", 
      "access"), 
      c("report", "report", "access", "access", "report", 
      "report", "report", "report", "report", "report", "data", "data", 
      "report", "access", "report", "report"), 
      c("report", "qlikview", 
      "gpa", "access", "gpa", "access"), 
      c("report", "gpa", "access", 
      "access", "gpa", "gpa", "gpa", "gpa", "gpa", "access", "gpa", 
      "gpa", "gpa", "report"), 
      c("report", "gpa", "gpa", "access", 
      "gpa", "access", "gpa", "access", "gpa", "gpa", "report", "gpa", 
      "gpa", "access", "gpa", "gpa", "gpa", "gpa", "gpa")) 
O <- as.data.frame(cbind(text)) 

rule <- function(out) { 
    vapply(out$text, function (row) { 
    if ("access" %in% row && ("gpa" %in% row || "qlikview" %in% row)) { 
     return("Access") 
    } else if ("report" %in% row && ("pfi" %in% row || "data" %in% row)) { 
     return("Report/Data") 
    } else { 
     return("NA") 
    } 
    }, "") 
} 

rule(O) 
# [1] "Access"  "Access"  "Access"  "Access"  "Access"  "Access"  "Report/Data" "Access"  
# [9] "Access"  "Access"