不能在 r 中的 across() 中使用 dplyr 编程语法
can not use dplyr programming syntax in across() in r
我想使用 dplyr 编程语法(结合 !!
和 :=
)来评估 .fn
参数中的函数但失败了。
代码如下:
library(zoo)
library(glue)
aa = structure(list(region = c(1, 2, 3, 4), co_mean = c(5, 5, 5, 5
), o3_mean = c(5, 5, 5, 5), pm2.5_mean = c(5, 5, 5, 5)), row.names = c(NA,
-4L), class = c("tbl_df", "tbl", "data.frame"))
for (i in 1:3) {
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa = aa %>% group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = list(!!fun_name_1 := ~lag(., i), # ERROR OCCUR AT HERE
!!fun_name_2 := ~ rollmeanr(., i)),
.names = '{.col}_{.fn}'))
aa
}
不知道怎么解决
非常感谢任何帮助!
======更新========
我的新代码和新错误:
library(zoo)
library(glue)
aa = structure(list(region = c(1, 2, 3, 4), co_mean = c(5, 5, 5, 5
), o3_mean = c(5, 5, 5, 5), pm2.5_mean = c(5, 5, 5, 5)), row.names = c(NA,
-4L), class = c("tbl_df", "tbl", "data.frame"))
for (i in 1:3) {
# i <- 1
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
aa
}
# Error: Problem with `mutate()` input `..1`.
# x 'names' attribute [6] must be the same length as the vector [5]
# i Input `..1` is `across(...)`.
# i The error occurred in group 1: region = 1.
# Run `rlang::last_error()` to see where the error occurred.
它将作为命名 list
工作。首先传递一组是非常有意义的(假设OP的原始示例数据每组有多行)
i <- 1
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
-输出
# A tibble: 4 x 10
# Groups: region [4]
# region co_mean o3_mean pm2.5_mean co_mean_lag1 co_mean_lag01 o3_mean_lag1 o3_mean_lag01 pm2.5_mean_lag1 pm2.5_mean_lag01
# <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#1 1 5 5 5 NA 5 NA 5 NA 5
#2 2 5 5 5 NA 5 NA 5 NA 5
#3 3 5 5 5 NA 5 NA 5 NA 5
#4 4 5 5 5 NA 5 NA 5 NA
可以在rollmean
中指定fill = TRUE
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i, fill = TRUE)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
首先我认为你的数据不应该被分组,至少对于共享的数据来说,在组中只有 1 行然后计算 lag
值和滚动平均值是没有意义的它。
您可以在 across
中使用 .names
获得适当的列名,并使用 map_dfc
将所有内容合并到一个数据框中。
library(dplyr)
library(purrr)
library(zoo)
map_dfc(1:3, function(x) {
aa %>%
transmute(across(.cols = contains('mean'),
.fns = list(lag = ~lag(., x),
lag0 = ~rollmeanr(., x, fill = NA)),
.names = sprintf('{fn}_{col}_%d', x)))
})
如果您在其他数据集上尝试,可以添加 group_by(Region)
。
我想使用 dplyr 编程语法(结合 !!
和 :=
)来评估 .fn
参数中的函数但失败了。
代码如下:
library(zoo)
library(glue)
aa = structure(list(region = c(1, 2, 3, 4), co_mean = c(5, 5, 5, 5
), o3_mean = c(5, 5, 5, 5), pm2.5_mean = c(5, 5, 5, 5)), row.names = c(NA,
-4L), class = c("tbl_df", "tbl", "data.frame"))
for (i in 1:3) {
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa = aa %>% group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = list(!!fun_name_1 := ~lag(., i), # ERROR OCCUR AT HERE
!!fun_name_2 := ~ rollmeanr(., i)),
.names = '{.col}_{.fn}'))
aa
}
不知道怎么解决
非常感谢任何帮助!
======更新========
我的新代码和新错误:
library(zoo)
library(glue)
aa = structure(list(region = c(1, 2, 3, 4), co_mean = c(5, 5, 5, 5
), o3_mean = c(5, 5, 5, 5), pm2.5_mean = c(5, 5, 5, 5)), row.names = c(NA,
-4L), class = c("tbl_df", "tbl", "data.frame"))
for (i in 1:3) {
# i <- 1
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
aa
}
# Error: Problem with `mutate()` input `..1`.
# x 'names' attribute [6] must be the same length as the vector [5]
# i Input `..1` is `across(...)`.
# i The error occurred in group 1: region = 1.
# Run `rlang::last_error()` to see where the error occurred.
它将作为命名 list
工作。首先传递一组是非常有意义的(假设OP的原始示例数据每组有多行)
i <- 1
fun_name_1 = glue('lag{i}')
fun_name_2 = glue('lag0{i}')
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
-输出
# A tibble: 4 x 10
# Groups: region [4]
# region co_mean o3_mean pm2.5_mean co_mean_lag1 co_mean_lag01 o3_mean_lag1 o3_mean_lag01 pm2.5_mean_lag1 pm2.5_mean_lag01
# <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#1 1 5 5 5 NA 5 NA 5 NA 5
#2 2 5 5 5 NA 5 NA 5 NA 5
#3 3 5 5 5 NA 5 NA 5 NA 5
#4 4 5 5 5 NA 5 NA 5 NA
可以在rollmean
fill = TRUE
aa %>%
group_by(region) %>%
mutate(across(.cols = contains('mean'),
.fns = setNames(list(~lag(., i),
~ rollmeanr(., i, fill = TRUE)), c(fun_name_1, fun_name_2)),
.names = '{.col}_{.fn}'))
首先我认为你的数据不应该被分组,至少对于共享的数据来说,在组中只有 1 行然后计算 lag
值和滚动平均值是没有意义的它。
您可以在 across
中使用 .names
获得适当的列名,并使用 map_dfc
将所有内容合并到一个数据框中。
library(dplyr)
library(purrr)
library(zoo)
map_dfc(1:3, function(x) {
aa %>%
transmute(across(.cols = contains('mean'),
.fns = list(lag = ~lag(., x),
lag0 = ~rollmeanr(., x, fill = NA)),
.names = sprintf('{fn}_{col}_%d', x)))
})
如果您在其他数据集上尝试,可以添加 group_by(Region)
。