Question

以下是我为dplyr编写的问题的代表：

library(tidyverse)

df <- tibble(State = c("A", "A", "A", "A", "A", "A", "B", "B", "B"),
             District_code = c(1:9),
                 District = c("North", "West", "North West", "South", "East", "South East", 
                              "XYZ", "ZYX", "AGS"), 
                 Population = c(1000000, 2000000, 3000000, 4000000, 5000000, 6000000, 
                                7000000, 8000000, 9000000))

df
#> # A tibble: 9 x 4
#>   State District_code District   Population
#>   <chr>         <int> <chr>           <dbl>
#> 1 A                 1 North         1000000
#> 2 A                 2 West          2000000
#> 3 A                 3 North West    3000000
#> 4 A                 4 South         4000000
#> 5 A                 5 East          5000000
#> 6 A                 6 South East    6000000
#> 7 B                 7 XYZ           7000000
#> 8 B                 8 ZYX           8000000
#> 9 B                 9 AGS           9000000

对于某些州，我需要将使用名称的地区合并到较少的地理类别中。特别是，状态A仅应具有：“北-西-西北”和“南-东-东南”。必须添加一些变量，例如人口。但其他人，例如District_code应该获得NA。我发现this example行之间的操作，但不是完全一样。 Grouping似乎不适用。

最终结果应该是这样的：

new_df
#> # A tibble: 5 x 4
#>   State District_code District                  Population
#>   <chr>         <int> <chr>                          <dbl>
#> 1 A                NA North - West - North West    5000000
#> 2 A                NA South - East - South East   15000000
#> 3 B                 7 XYZ                          7000000
#> 4 B                 8 ZYX                          8000000
#> 5 B                 9 AGS                          9000000

在实际数据框中，必须添加一些变量（如“人口”）以及许多其他变量（例如“区号”），这些变量必须获取NA值。

感谢您的帮助！

Answer 1

您可以使用fct_collapse指定新的因子水平，然后在新组上使用summarise。

df %>%
  mutate(District = 
           fct_collapse(District, 
                        "North - West - North West" = c("North", "West", "North West"), 
                        "South - East - South East" = c("South", "East", "South East"))) %>% 
  group_by(State, District) %>% 
  summarise(Population = sum(Population), 
            District_code = ifelse(n() > 1, NA_real_, District_code))

# A tibble: 5 x 3
# Groups:   State [?]
#   State District                  Population
#   <chr> <fct>                          <dbl>
# 1 A     South - East - South East   15000000
# 2 A     North - West - North West    6000000
# 3 B     AGS                          9000000
# 4 B     XYZ                          7000000
# 5 B     ZYX                          8000000

如果您只想更改某些特定州的地区，则可以像这样添加case_when或if_else，并在列的类型上设置汇总功能（此处为“人口”的两倍）反对该地区的整数）

df %>%
  mutate(District = 
           case_when(State == "A" ~ 
                       fct_collapse(District, 
                                    "North - West - North West" = c("North", "West", "North West"), 
                                    "South - East - South East" = c("South", "East", "South East")), 
                     TRUE ~ factor(District))) %>% 
  group_by(State, District) %>% 
  summarise_all(funs({if(is.double(.)) {
    sum(.) 
  } else {
    if (length(unique(.)) > 1) {
      NA
    } else {
      unique(.)
    }
  }}))

Answer 2

对于某些州，我需要将使用名称的地区合并到较少的地理类别中。特别是，状态A仅应具有：“北-西-西北”和“南-东-东南”。

您需要写下分组规则，例如...

merge_rules = list(
  list(State = "A", District = c("North", "West", "North West")),
  list(State = "A", District = c("South", "East", "South East"))
)

必须添加一些变量，例如人口。但是其他人，例如District_code应该获得NA。

我可以通过将合并规则放在表格中来做到这一点；合并后进行计算；并在未合并的行上进行rbind-ing。这是data.table的方式...

library(data.table)
DT  = data.table(df)
mDT = rbindlist(lapply(merge_rules, as.data.table), id = "g")

gDT = DT[mDT, on=.(State, District)][, .(
  District_code = District_code[NA_integer_],
  District = paste(District, collapse = " - "),
  Population = sum(Population)
), by=.(g, State)]

rbind(
  DT[!mDT, on=.(State, District)],
  gDT[, !"g"]
)[order(State, District)]

   State District_code                  District Population
1:     A            NA North - West - North West    6.0e+06
2:     A            NA South - East - South East    1.5e+07
3:     B             9                       AGS    9.0e+06
4:     B             7                       XYZ    7.0e+06
5:     B             8                       ZYX    8.0e+06

而且，我想，tidyverse的方式是类似的：

mtib = bind_rows(lapply(merge_rules, as.tibble), .id = "g")

gtib = right_join(df, mtib, by=c("State", "District")) %>% 
  group_by(g, State) %>% summarise(
    District_code = District_code[NA_integer_],
    District = paste(District, collapse = " - "),
    Population = sum(Population)    
  )

bind_rows(
  anti_join(df, mtib, by=c("State", "District")),
  gtib %>% ungroup %>% select(-g)
) %>% arrange(State, District)

# A tibble: 5 x 4
  State District_code District                  Population
  <chr>         <int> <chr>                          <dbl>
1 A                NA North - West - North West    6000000
2 A                NA South - East - South East   15000000
3 B                 9 AGS                          9000000
4 B                 7 XYZ                          7000000
5 B                 8 ZYX                          8000000

Answer 3

这是获取州A的总人口的一种方法：

df %>% 
  filter(State == "A") %>%
  mutate(`North - West - North West` = (District == "North"|District == "West"|District == "North West"), 
         `South - East - South East` = (District == "South"|District == "East"|District == "South East")) %>% 
  gather(key = Districts, value = present, 5:6) %>% 
  filter(present != FALSE) %>% 
  group_by(Districts) %>% 
  summarise(Population = sum(Population))

哪个给出输出：

  Districts          Population
  <chr>                   <dbl>
1 North - West - No…    6000000
2 South - East - So…   15000000

有人应该能够帮助我们将以上内容放入原始df中。

合并和部分添加R

3 个答案: