如何使用不同的过滤器总结n = n？

如何解决如何使用不同的过滤器总结n = n？

我想打印以下表格。enter image description here 我尝试了几种方法，但我只能添加具有该类型信息的列之一（“to_ORD”或“to_MDW”）。我如何编码才能同时在同一张桌子上获取它们？

这是我的代码：

library(tidyverse)
library(dplyr)
install.packages("nycflights13")
library(nycflights13)
flights_1 <- flights %>%
    group_by(carrier) %>%
    filter(dest == "ORD") %>%
    summarize(to_ORD = n())
flights_1
flights_2 <- flights %>%
    group_by(carrier) %>%
    filter(dest == "MDW") %>%
    summarize(to_MDW = n())
flights_2

我也试过：（显然不正确）

flights_1 <- flights %>%
    group_by(carrier) %>%
    filter(dest == "ORD"| dest == "MDW") %>%
    summarize(to_ORD = n())

解决方法

对于每个 carrier 计算 'ORD' 和 'MDW' 值的计数，并仅保留任何值大于 0 的那些行。

library(dplyr)

flights %>%
  group_by(carrier) %>%
  summarize(to_ORD = sum(dest == "ORD"),to_MDW = sum(dest == "MDW")) %>%
  filter(to_ORD > 0 | to_MDW > 0)

#  carrier to_ORD to_MDW
#  <chr>    <int>  <int>
#1 9E        1056      0
#2 AA        6059      0
#3 B6         905      0
#4 EV           2      0
#5 MQ        2276      0
#6 OO           1      0
#7 UA        6984      0
#8 WN           0   4113

,

沿着相同的路线，但有更多步骤来说明推理，即消除不必要的数据，然后区分两个芝加哥地区的机场。

library(dplyr)
library(nycflights13)
flights %>% 
  filter(dest == "ORD" | dest == "MDW") %>%
  group_by(carrier,dest) %>%
  count() %>%
  mutate(to_ORD = ifelse(dest == "ORD",n,0),to_MDW = ifelse(dest == "MDW",0)) %>%
  select(-dest,-n)
#> Adding missing grouping variables: `dest`
#> # A tibble: 8 x 4
#> # Groups:   carrier,dest [8]
#>   dest  carrier to_ORD to_MDW
#>   <chr> <chr>    <dbl>  <dbl>
#> 1 ORD   9E        1056      0
#> 2 ORD   AA        6059      0
#> 3 ORD   B6         905      0
#> 4 ORD   EV           2      0
#> 5 ORD   MQ        2276      0
#> 6 ORD   OO           1      0
#> 7 ORD   UA        6984      0
#> 8 MDW   WN           0   4113

,

我们可以使用pivot_wider

library(dplyr)
library(nycflights13)
library(tidyr)
flights %>% 
  select(carrier,dest) %>% 
  filter(dest %in% c("ORD","MDW")) %>% 
  pivot_wider(names_from = dest,values_from = dest,values_fn = length,values_fill = 0)

-输出

# A tibble: 8 x 3
#  carrier   ORD   MDW
#  <chr>   <int> <int>
#1 UA       6984     0
#2 AA       6059     0
#3 MQ       2276     0
#4 B6        905     0
#5 WN          0  4113
#6 9E       1056     0
#7 OO          1     0
#8 EV          2     0

---

或者将 base R 与 table 和 subset 一起使用

table(subset(flights,dest %in% c("ORD","MDW"),select = c(carrier,dest)))