Question

我被困住了。如何使用dplyr's filter()

将两个关系运算符同时用作组内组内的过滤器

我得到了什么

数据，

# install.packages(c("tidyverse"), dependencies = TRUE)
library(tibble)
tbl <- structure(list(id1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
           2L, 2L, 2L, 2L, 2L, 2L), id2 = c("x_02", "x_02", "x_02", "x_02", "x_02", "x_02",
           "x_02", "x_02", "x_02", "x_02", "x_02", "x_02", "x_02", "x_03", "x_03", "x_03",
           "x_03", "x_03", "x_03", "x_03", "x_03"), x = c(-4L, -3L, -2L, -1L, 1L, 2L, 3L,
           4L, 5L, -2L, -1L, 1L, 2L, -2L, -1L, 1L, 2L, 3L, 4L, 5L, 6L)),
           class = c("grouped_df", "tbl_df", "tbl", "data.frame"), row.names = c(NA, -21L),
           vars = c("id1", "id2"), drop = TRUE, .Names = c("id1", "id2", "x"),
           indices = list(0:8, 9:12, 13:20), group_sizes = c(9L, 4L, 8L),
           biggest_group_size = 9L, labels = structure(list(id1 = c(1L, 2L, 2L),
           id2 = c("x_02", "x_02", "x_03")), class = "data.frame", row.names = c(NA, -3L),
           vars = c("id1", "id2"), drop = TRUE, .Names = c("id1", "id2")))

tbl
#> # A tibble: 21 x 3
#> # Groups:   id1, id2 [3]
#>      id1   id2     x
#>    <int> <chr> <int>
#>  1     1  x_02    -4
#>  2     1  x_02    -3
#>  3     1  x_02    -2
#>  4     1  x_02    -1
#>  5     1  x_02     1
#>  6     1  x_02     2
#>  7     1  x_02     3
#>  8     1  x_02     4
#>  9     1  x_02     5
#> 10     2  x_02    -2
#> # ... with 11 more rows

简而言之，我想在id1内的id2内查找，并找到一系列从x开始到x < -2结束的x > 2（在mig下面的期望的结果说明它比我在这里描述的更好。）

在某种程度上，我将其视为两个过滤器的组合，即我想要这个过滤器，

library(dplyr)
tbl %>% group_by(id1, id2) %>%
   filter( (row_number() == n() & x >  2 ) )
#> # A tibble: 2 x 3
#> # Groups:   id1, id2 [2]
#>     id1   id2     x
#>   <int> <chr> <int>
#> 1     1  x_02     5
#> 2     2  x_03     6

与此过滤器结合使用，

tbl %>% group_by(id1, id2) %>%
   filter( (row_number() == 1 & x < -2 )  )
#> # A tibble: 1 x 3
#> # Groups:   id1, id2 [1]
#>     id1   id2     x
#>   <int> <chr> <int>
#> 1     1  x_02    -4

我认为，这是类似的东西，但这并没有给我任何数据。

tbl %>% group_by(id1, id2) %>%
   filter( (row_number() == n() & x >  2 ) &
           (row_number() == 1   & x < -2 )  )

为什么不给这个？

我想获得什么/期望的结果

# A tibble: 2 x 3
# Groups:   id1, id2 [1]
    id1   id2     x
  <int> <chr> <int>
1     1  x_02    -4
1     1  x_02     5

Answer 1

如果组内满足两个条件，则该组应该有2行，因此只需再次过滤n() == 2

tbl %>%
  filter((row_number() == n() & x > 2 ) | (row_number() == 1 & x < -2 )) %>%
  filter(n() == 2)

# A tibble: 2 x 3
# Groups: id1, id2 [1]
    # id1 id2       x
  # <int> <chr> <int>
# 1     1 x_02     -4
# 2     1 x_02      5

尝试额外的（见评论）：

tbl %>%
  filter((row_number() == n() & x > 2 ) | (row_number() == 1 & x < -2 )) %>%
  filter(n() == 2) %>%
  distinct(id1, id2) %>%
  left_join(., tbl, by=c("id1", "id2"))

使用dplyr的filter（）进行过滤 - 使用关系运算符

我得到了什么

我想获得什么/期望的结果

1 个答案: