`if_else` 多个（动态指定的）列的条件
`if_else` condition on multiple (dynamically specified) columns
我正在尝试 mutate 基于多个现有列的值的新列，这样如果任何列等于指定值，if_else 的计算结果为 TRUE。我可以使用 if_else 中的多个比较表达式来执行此操作，但这不起作用，因为我需要使用准引用动态指定列。 Reprex 下面有解释性注释。
如有任何关于如何评估多个动态指定列的比较的建议，我将不胜感激。
提前感谢您的帮助！
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
mtcars <- head(mtcars, 8)
# Desired output, using individual comparisons for each column
mtcars %>%
mutate(color = if_else(
(gear == 4 | carb == 4),
"purple",
"green")
)
#> mpg cyl disp hp drat wt qsec vs am gear carb color
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 green
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 green
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 green
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
# Failed attempts to do comparisons on multiple columns
mtcars %>%
mutate(color = if_else(
(gear|carb == 4),
"purple",
"green")
)
#> mpg cyl disp hp drat wt qsec vs am gear carb color
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 purple
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 purple
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 purple
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
mtcars %>%
mutate(color = if_else(
(c(gear, carb) == 4),
"purple",
"green")
)
#> Error: Problem with `mutate()` input `color`.
#> x Input `color` can't be recycled to size 8.
#> ℹ Input `color` is `if_else((c(gear, carb) == 4), "purple", "green")`.
#> ℹ Input `color` must be size 8 or 1, not 16.
# Using dynamically specified columns and quasiquotation
my_vars <- c("gear", "carb")
# Quasiquotation works with `select`, and `coalesce`
mtcars %>% select(!!!syms(my_vars))
#> gear carb
#> Mazda RX4 4 4
#> Mazda RX4 Wag 4 4
#> Datsun 710 4 1
#> Hornet 4 Drive 3 1
#> Hornet Sportabout 3 2
#> Valiant 3 1
#> Duster 360 3 4
#> Merc 240D 4 2
mtcars %>% mutate(any_value = coalesce(!!!syms(my_vars)))
#> mpg cyl disp hp drat wt qsec vs am gear carb any_value
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 4
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 4
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 4
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 3
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 3
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 3
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 3
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 4
# Desired `mutate`: if any columns (via quasiquotation) == 4, then TRUE
mtcars %>%
mutate(color = if_else(
any(!!!syms(my_vars) == 4),
"purple",
"green")
)
#> Error in splice(dot_call(capture_dots, frame_env = frame_env, named = named, : 'list' object cannot be coerced to type 'double'
由 reprex package (v0.3.0)
于 2020-08-17 创建
mtcars %>%
mutate(
flag = eval(parse(text = str_c(my_vars, " == 4", collapse = "|"))),
color = if_else(flag, "purple", "green")
) %>%
select(-flag)
您可以对要检查的列进行子集化，将它们与值进行比较，然后rowSums计算它们的出现次数并据此分配值。
mtcars$any_value <- ifelse(rowSums(mtcars[my_vars] == 4) > 0, 'purple', 'green')
#Without ifelse
mtcars$any_value <- c('green', 'purple')[(rowSums(mtcars[my_vars] == 4) > 0) + 1]
mtcars
# mpg cyl disp hp drat wt qsec vs am gear carb any_value
#Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 green
#Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 green
#Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 green
#Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
tidyverse 方法可以使用 rowwise 和 c_across
library(dplyr)
mtcars %>%
rowwise() %>%
mutate(any_value= if(any(c_across(all_of(my_vars)) == 4)) 'purple' else 'green')
我正在尝试 mutate 基于多个现有列的值的新列，这样如果任何列等于指定值，if_else 的计算结果为 TRUE。我可以使用 if_else 中的多个比较表达式来执行此操作，但这不起作用，因为我需要使用准引用动态指定列。 Reprex 下面有解释性注释。
如有任何关于如何评估多个动态指定列的比较的建议，我将不胜感激。
提前感谢您的帮助！
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
mtcars <- head(mtcars, 8)
# Desired output, using individual comparisons for each column
mtcars %>%
mutate(color = if_else(
(gear == 4 | carb == 4),
"purple",
"green")
)
#> mpg cyl disp hp drat wt qsec vs am gear carb color
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 green
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 green
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 green
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
# Failed attempts to do comparisons on multiple columns
mtcars %>%
mutate(color = if_else(
(gear|carb == 4),
"purple",
"green")
)
#> mpg cyl disp hp drat wt qsec vs am gear carb color
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 purple
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 purple
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 purple
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
mtcars %>%
mutate(color = if_else(
(c(gear, carb) == 4),
"purple",
"green")
)
#> Error: Problem with `mutate()` input `color`.
#> x Input `color` can't be recycled to size 8.
#> ℹ Input `color` is `if_else((c(gear, carb) == 4), "purple", "green")`.
#> ℹ Input `color` must be size 8 or 1, not 16.
# Using dynamically specified columns and quasiquotation
my_vars <- c("gear", "carb")
# Quasiquotation works with `select`, and `coalesce`
mtcars %>% select(!!!syms(my_vars))
#> gear carb
#> Mazda RX4 4 4
#> Mazda RX4 Wag 4 4
#> Datsun 710 4 1
#> Hornet 4 Drive 3 1
#> Hornet Sportabout 3 2
#> Valiant 3 1
#> Duster 360 3 4
#> Merc 240D 4 2
mtcars %>% mutate(any_value = coalesce(!!!syms(my_vars)))
#> mpg cyl disp hp drat wt qsec vs am gear carb any_value
#> 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 4
#> 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 4
#> 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 4
#> 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 3
#> 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 3
#> 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 3
#> 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 3
#> 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 4
# Desired `mutate`: if any columns (via quasiquotation) == 4, then TRUE
mtcars %>%
mutate(color = if_else(
any(!!!syms(my_vars) == 4),
"purple",
"green")
)
#> Error in splice(dot_call(capture_dots, frame_env = frame_env, named = named, : 'list' object cannot be coerced to type 'double'
由 reprex package (v0.3.0)
于 2020-08-17 创建mtcars %>%
mutate(
flag = eval(parse(text = str_c(my_vars, " == 4", collapse = "|"))),
color = if_else(flag, "purple", "green")
) %>%
select(-flag)
您可以对要检查的列进行子集化，将它们与值进行比较，然后rowSums计算它们的出现次数并据此分配值。
mtcars$any_value <- ifelse(rowSums(mtcars[my_vars] == 4) > 0, 'purple', 'green')
#Without ifelse
mtcars$any_value <- c('green', 'purple')[(rowSums(mtcars[my_vars] == 4) > 0) + 1]
mtcars
# mpg cyl disp hp drat wt qsec vs am gear carb any_value
#Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 purple
#Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 purple
#Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 purple
#Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 green
#Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 green
#Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 green
#Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 purple
#Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 purple
tidyverse 方法可以使用 rowwise 和 c_across
library(dplyr)
mtcars %>%
rowwise() %>%
mutate(any_value= if(any(c_across(all_of(my_vars)) == 4)) 'purple' else 'green')