在 R 中解析“大陆/国家/城市”向量的快速方法 基准数据

如何解决在 R 中解析“大陆/国家/城市”向量的快速方法 基准数据

我在 R 中有一个字符向量，每个字符串由“大陆/国家/城市”组成，例如

x=rep("Africa / Kenya / Nairobi",1000000)

但是“ / ”偶尔会在没有括号空格的情况下被错误输入为“/”，并且在某些情况下城市也丢失了，因此它会例如是“非洲/肯尼亚”，没有城市。

我想将其解析为三个向量 大洲、国家和城市，如果缺少城市，则使用 NA。

对于国家，我现在做了类似的事情

country = sapply(x,function(loc) trimws(strsplit(loc,"/",fixed = TRUE)[[1]][2]))

但是如果向量 x 很长，那会很慢。在 R 中解析它的有效方法是什么？

解决方法

您可以在 rbind 中尝试 do.call。在 [ 中使用 lapply 是为了在城市缺失的情况下获得 3 个结果。

x <- c("Africa / Kenya / Nairobi","Africa/Kenya/Nairobi","Africa / Kenya")

y <- do.call(rbind,lapply(strsplit(x,"/",TRUE),"[",1:3))
y <- trimws(y,whitespace = " ")

y
#     [,1]     [,2]    [,3]     
#[1,] "Africa" "Kenya" "Nairobi"
#[2,] "Africa" "Kenya" "Nairobi"
#[3,] "Africa" "Kenya" NA       

或者使用data.table：

x <- c("Africa / Kenya / Nairobi","Africa / Kenya")

y <- do.call(cbind,data.table::tstrsplit(x,TRUE))
y <- trimws(y,] "Africa" "Kenya" NA       

---

基准

#x <- rep("Africa / Kenya / Nairobi",1000000) #Timings will depend on the used dataset

n <- 1e6L
f1 <- function(n) replicate(n,paste(sample(letters,sample(5:15,1),collapse = ""))
f2 <- function(n) sample(c("/"," /","/ "," / "),n,TRUE)
set.seed(42)
x <- paste0(f1(n),f2(n),f1(n),sample(c(paste0(f2(n%/%2L),f1(n%/%2L)),rep("",n - n%/%2L))))

system.time( #Method given in the question
  sapply(x,function(loc) trimws(strsplit(loc,fixed = TRUE)[[1]][2])))
#       User      System verstrichen 
#     47.718       0.004      47.798 

system.time(  #Using strsplit and trimws
  trimws(do.call(rbind,1:3)),whitespace = " "))
#       User      System verstrichen 
#      5.446       0.008       5.454 

system.time(  #Using data.table::tstrsplit and trimws
  trimws(do.call(cbind,TRUE)),whitespace = " "))
#       User      System verstrichen 
#      2.365       0.012       2.376 

system.time(  #Using readr::read_delim from @Anoushiravan R
  readr::read_delim(x,delim = "/",quote = "",trim_ws = TRUE,col_names = FALSE))
#       User      System verstrichen 
#      1.961       0.024       2.222 

system.time(  #Using data.table::tstrsplit with " */ *"
  do.call(cbind," */ *",perl=TRUE)))
#       User      System verstrichen 
#      1.394       0.000       1.394 

system.time(  #Using read.table from @akrun
  read.table(text = x,sep = "/",header = FALSE,fill = TRUE,strip.white = TRUE,na.strings = ""))
#       User      System verstrichen 
#      1.298       0.004       1.302 

system.time(  #Using data.table::fread from @akrun
  data.table::fread(text = paste(x,collapse="\n"),sep="/",na.strings = ""))
#       User      System verstrichen 
#      1.146       0.016       0.996 

system.time(  #Using read.table with additional argiments
  read.table(text = x,na.strings = "",nrows=length(x),comment.char = "",colClasses = c("character")))
#       User      System verstrichen 
#      1.076       0.000       1.076 

system.time(  #Using data.table::fread with stringr::str_c (or stringi::stri_c)
  data.table::fread(text = stringr::str_c(x,na.strings = ""))
#       User      System verstrichen 
#      0.780       0.000       0.624 

使用 data.table::fread 并使用 stringr::str_c 创建输入字符串看起来是目前给定方法中最快的。

,

考虑使用 gcloud projects get-iam-policy $GCP_PROJECT_NAME \ --filter="serviceAccount" \ --flatten="bindings[].members" \ --format="value(bindings.members.split(':').slice(1:).flatten())" \ --sort-by=bindings.members | uniq #=> . . . $SOME_SERVICE_ACCOUNT . . . 中的 read.table

base R

或者使用 read.table(text = x,na.strings = "") V1 V2 V3 1 Africa Kenya Nairobi 2 Africa Kenya Nairobi 3 Africa Kenya <NA> 中的 fread

data.table

基准

library(data.table)
fread(text = paste(x,na.strings = "")
   Africa Kenya Nairobi
1: Africa Kenya Nairobi
2: Africa Kenya    <NA>

数据

x <- rep("Africa / Kenya / Nairobi",1000000)
> 
> system.time(fread(text = paste(x,na.strings = ""))
   user  system elapsed 
  0.473   0.024   0.496 

> system.time(read.table(text = x,+       fill = TRUE,na.strings = ""))
   user  system elapsed 
  0.519   0.026   0.543 

> system.time({  #Using data.table
+   y <- do.call(cbind,TRUE))
+   y <- trimws(y,whitespace = " ")
+ })
   user  system elapsed 
  2.035   0.051   2.067 

,

我认为这也可以使用：

library(readr)

xx <- readr::read_delim(b,col_names = FALSE)

# A tibble: 3 x 3
  X1     X2    X3     
  <chr>  <chr> <chr>  
1 Africa Kenya Nairobi
2 Africa Kenya Nairobi
3 Africa Kenya NA