2

非常感谢帮助！！！

我有一些非常脏的数据要清理。在 R 中寻找一个优雅的解决方案，可以正确识别是否有国外旅行（TRUE = 国外旅行，FALSE = 国内/美国旅行）。

数据存在几个问题，包括： - 州都是缩写格式和非缩写格式 - 拼写错误 - 不同的格式（即只有州、城市逗号州、城市斜线州等） - 州/国家下的数据可能包含城市而不是一个州/国家，反之亦然，用于城市列。

在外国旅行列下，解决方案应该覆盖这样，如果州/国家或城市列指示外国旅行，它将被编码为 TRUE，否则为 FALSE。

   `State/Country`          `Foreign Travel`                   City         
    <chr>                            <lgl>                    <chr>        
   1 CA                                FALSE             San Francisco
   2 California                        FALSE             San Francisco
   3 British Columbia, Canada          TRUE              Vancouver    
   4 Florida                            NA               Hollywood    
   5 TX                                 NA               Dallas       
   6 Florda                             NA               Orlando 
   7 FL/CA                              NA               Orlando, Sacramennto 
   8 bufalo                             NA               NY
   9 d.c                               FALSE             washington dc
   10 frt wort, tx                     FALSE             texass
   11 frt wort, tx                     FALSE             texass
   12 japan                            NA                japan
   13 W?rzburg                         FALSE             german

现在我有一些非常不整洁的代码，它查看每一列，如果找到它，给出一个真/假，如果它为至少 1 列的真（找到一个国内项目）它由外国 t/f 列重新编码为假（没有外国旅行）：

 ##add some lines for nas
 no_entry <- c("na",".","","n/a","none")
  ##Maps package
 cities<- world.cities

 USAcities <- cities %>%
    filter(country.etc == 'USA')

   USAcities <- c(USAcities, 'williamsburg')

  USAcities <-tolower(USAcities$name)
 USA_fullState<- tolower(USA_fullState)
 USA_stateABR<- tolower(USA_stateABR)
 Travel_df_limited$State.Country<- tolower(Travel_df_limited$State.Country)


     Travel_df_limited$ForeignTravel_rc1 <- 
    c(rep(0,length(Travel_df_limited$Foreign.Travel)))

   i<-1
   for (i in 1:length(USA_fullState)){
   Travel_df_limited <- Travel_df_limited %>%
    mutate(ForeignTravel_rc1 = 
    ifelse(grepl(USA_fullState[i],Travel_df_limited$State.Country) == 
    "TRUE","FALSE",Travel_df_limited$ForeignTravel_rc1 ))
     i<- i+1}

  Travel_df_limited$ForeignTravel_rc1

   Travel_df_limited <- Travel_df_limited %>%
    mutate(ForeignTravel_rc2 = ifelse(Travel_df_limited$State.Country%in% 
    USA_stateABR== "TRUE","FALSE","TRUE"))


 Travel_df_limited$ForeignTravel_rc3 <- 
    c(rep(0,length(Travel_df_limited$Foreign.Travel)))

   i<-1
 for (i in 1:length(USAcities)){
   Travel_df_limited <- Travel_df_limited %>%
    mutate(ForeignTravel_rc3 = 
     ifelse(grepl(USAcities[i],Travel_df_limited$State.Country) == 
    "TRUE","FALSE",Travel_df_limited$ForeignTravel_rc3))
     i<- i+1}


     Travel_df_limited <- Travel_df_limited %>%
     mutate(ForeignTravel_rc = ifelse(Travel_df_limited$ForeignTravel_rc1 == 
      "FALSE" |   Travel_df_limited$ForeignTravel_rc2 == "FALSE"|
                                 Travel_df_limited$ForeignTravel_rc3 == 
          "FALSE" , "FALSE",
             ifelse(Travel_df_limited$State.Country%in% 
               c("na",".","","n/a","none") =="TRUE","FALSE", "TRUE")))



      Travel_df_limited<- subset(Travel_df_limited, select = - 
       c(ForeignTravel_rc1,ForeignTravel_rc2,ForeignTravel_rc3))
4

0 回答 0