Question

每个人的好日子，

我在完成这项具有挑战性的任务时遇到了麻烦，我希望找到一种优雅的方法：

我需要在＆＃39; Zone＆＃39;
从＆＃39; country_name＆＃39;中逐行提取多个子字符串。按区域分组＆＃39;元素
将行方式的多个子字符串存储为用于对df2
将索引值与df2
计算总人口并根据df1

基本上面临的挑战是，不应该针对数据框中的任何特定元素修复该方法。

第一个数据帧：

df1 <- data.frame(zone, country_name)
zone = c("M", "N", "O")
country_name = c("The USA, Canada & Mexico are part of North America", "Canada like Australia is a Commonwealth member", "The UK is still finalizing its exit plans from the EU")

第二个数据帧：

df2 <- data.frame(zonal_region, country, population)
zonal_region = c("M", "M", "M", "N", "N", "N", "O", "O", "O")
country = c("USA", "Canada", "Mexico", "Canada", "Australia", "UK", "Australia", "UK", "Canada")
population = c(323.4 , 36.29, 127.5, 36.29, 24.13, 65.64, 24.13, 65.64, 36.29)

这是我的最终输出结果：

df3 <- data.frame(zone, country_name, total_population)
zone = c("M", "N", "O")
country_name = c("The USA, Canada & Mexico are part of North America", "Canada like Australia is a Commonwealth member", "The UK is still finalizing its exit plans from the EU")
total_population = c(487.19, 60.42, 65.64)

我一直无法提取多个子字符串并根据其区域对df2索引其值。

如果有人能解决这个问题，我们将非常感激。

谢谢！

Answer 1

我们可以通过在提取“国家/地区”后对这两个数据集进行left/right联接来实现此目的。来自＆＃39; country_name＆＃39; ＆＃39; df1＆＃39;列，并执行group_by sum

library(tidyverse)
un1 <- unique(df2$country)
df1 %>%
   mutate(cntry =  str_extract_all(country_name, paste(un1, collapse="|"))) %>% 
   right_join(df2, by = c('zone' = 'zonal_region')) %>% 
   group_by(zone) %>% 
   summarize(total_population= sum(population[country %in% cntry[[1]]])) %>% 
   left_join(df1) %>%
   select(zone, country_name, total_population)
# A tibble: 3 x 3
#  zone  country_name                                          total_population
  <fct> <fct>                                                            <dbl>
#1 M     The USA, Canada & Mexico are part of North America               487. 
#2 N     Canada like Australia is a Commonwealth member                    60.4
#3 O     The UK is still finalizing its exit plans from the EU             65.6

Answer 2

您可以尝试fuzzyjoin

library(dplyr)
library(stringr)
library(fuzzyjoin)

df1 %>% 
  mutate_if(is.factor, as.character) %>%
  fuzzy_left_join((df2 %>% mutate_if(is.factor, as.character)),
                  by = c("zone" = "zonal_region", "country_name" = "country"), 
                  match_fun = str_detect) %>%
  group_by(zone, country_name) %>%
  summarise(total_population = sum(population)) %>%
  data.frame()

输出为：

  zone                                          country_name total_population
1    M    The USA, Canada & Mexico are part of North America           487.19
2    N        Canada like Australia is a Commonwealth member            60.42
3    O The UK is still finalizing its exit plans from the EU            65.64

示例数据：

df1 <- structure(list(zone = structure(1:3, .Label = c("M", "N", "O"
), class = "factor"), country_name = structure(c(3L, 1L, 2L), .Label = c("Canada like Australia is a Commonwealth member", 
"The UK is still finalizing its exit plans from the EU", "The USA, Canada & Mexico are part of North America"
), class = "factor")), class = "data.frame", row.names = c(NA, 
-3L))

df2 <- structure(list(zonal_region = structure(c(1L, 1L, 1L, 2L, 2L, 
2L, 3L, 3L, 3L), .Label = c("M", "N", "O"), class = "factor"), 
    country = structure(c(5L, 2L, 3L, 2L, 1L, 4L, 1L, 4L, 2L), .Label = c("Australia", 
    "Canada", "Mexico", "UK", "USA"), class = "factor"), population = c(323.4, 
    36.29, 127.5, 36.29, 24.13, 65.64, 24.13, 65.64, 36.29)), class = "data.frame", row.names = c(NA, 
-9L))

有条件地使用grepl提取多个子字符串，索引提取以返回累积值

2 个答案: