使用引用替换多个值 table

Question

我正在清理一个数据库，其中一个字段是“国家”，但是我数据库中的国家名称与我需要的输出不匹配。

虽然我想使用 str_replace 功能，但我有超过 50 个国家需要修复，所以这不是最有效的方法。我已经准备了一个 CSV 文件，其中包含我需要参考的原始国家/地区输入和输出。

这是我目前的情况：

library(stringr)
library(dplyr)
library(tidyr)
library(readxl)
database1<- read_excel("database.xlsx") 
database1$country<str_replace(database1$country,"USA","United States")
database1$country<str_replace(database1$country,"UK","United Kingdom")
database1$country<str_replace(database1$country,"Bolivia","Bolivia,Plurinational State of")
write.csv(database1, "test.csv", row.names=FALSE, fileEncoding = 'UTF 8', na="")

Answer 1

注意：factor 中的级别和标签必须是唯一的，否则不应包含重复项。

# database1 <- read_excel("database.xlsx")  ## read database excel book
old_names <- c("USA", "UGA", "CHL") ## country abbreviations
new_names <- c("United States", "Uganda", "Chile")  ## country full form

基础 R

database1 <- within( database1, country <- factor( country, levels = old_names, labels = new_names ))

Data.Table

library('data.table')
setDT(database1)
database1[, country := factor(country, levels = old_names, labels = new_names)]

database1
#          country
# 1: United States
# 2:        Uganda
# 3:         Chile
# 4: United States
# 5:        Uganda
# 6:         Chile
# 7: United States
# 8:        Uganda
# 9:         Chile

数据

database1 <- data.frame(country = c("USA", "UGA", "CHL", "USA", "UGA", "CHL", "USA", "UGA", "CHL"))
#    country
# 1     USA
# 2     UGA
# 3     CHL
# 4     USA
# 5     UGA
# 6     CHL
# 7     USA
# 8     UGA
# 9     CHL

编辑： 您可以创建一个命名向量 countries，而不是两个变量，例如 old_names 和 new_names.

countries <- c("USA", "UGA", "CHL")
names(countries) <- c("United States", "Uganda", "Chile")
within( database1, country <- factor( country, levels = countries, labels = names(countries) ))

Answer 2

过去曾使用类似的方法使用 .csv 文件进行批量替换，解决过类似的问题。

.csv 文件格式示例：

library(data.table)

## Generate example replacements csv file to see the format used
Replacements <- data.table(Old = c("USA","UGA","CHL"),
                           New = c("United States", "Uganda", "Chile"))

fwrite(Replacements,"Replacements.csv")

获得 "Replacements.csv" 后，您可以使用它一次性替换所有名称 stringi::replace_all_regex()。（对于它的价值，几乎整个 stringr 包本质上是对 stringi 调用的包装。由于 stringi 运行速度稍快并且具有更大的功能集，我更愿意坚持stringi.) See stringi vs stringr blog by HRBRMSTR

library(data.table)
library(readxl)
library(stringi)

## Read in list of replacements
Replacements <- fread("Replacements.csv")

## Read in file to be cleaned
database1<- read_excel("database.xlsx")

## Perform Replacements
database1$countries <- stringi::stri_replace_all_regex(database1$countries,
                                              "^"%s+%Replacements$Old%s+%"$",
                                              Replacements$New,
                                              vectorize_all = FALSE)

## Write CSV
write.csv(database1, "test.csv", row.names=FALSE, fileEncoding = 'UTF 8', na="")

我尝试在可能的情况下使用上面的基础 R data.frame 语法以避免任何混淆，但如果我这样做是为了我自己，我会坚持使用完整的 data.table 语法，如下所示：

library(data.table)
library(readxl)
library(stringi)

## Read in list of replacements
Replacements <- fread("Replacements.csv")

## Read in file to be cleaned
database1<- read_excel("database.xlsx")

## Perform Replacements
database1[, countries := stri_replace_all_regex(countries,"^"%s+%Replacements[,Old]%s+%"$",
                                              Replacements[,New],
                                              vectorize_all = FALSE)]
## Write CSV
fwrite(database1,"test.csv")

使用引用替换多个值 table

Replace multiple values using a reference table

r

countries

stringr

data-cleaning