1

我正在尝试清理我的代码以清理丢失的数据。我有一个包含 6 列的数据集，如果我像这样单独执行它们，则代码可以工作：

mammographic_masses <- mammographic_masses %>%
  mutate(birad = replace(birad, birad== "na", NA)) %>%
  mutate(birad = replace(birad, birad== "N/A", NA))

但是当我尝试在这样的 for 循环中执行此操作时：

for (i in ncol(mammographic_masses)){
  print(class(mammographic_masses[[i]]))
  mammographic_masses <- mammographic_masses %>%
    mutate(mammographic_masses[[,i]] = replace(mammographic_masses[[,i]], mammographic_masses[[,i]] == "na", NA)) %>%
    mutate(mammographic_masses[[,i]] = replace(mammographic_masses[[,i]], mammographic_masses[[,i]] == "N/A", NA))
}

我收到一个错误：

Error: unexpected '=' in:
"  mammographic_masses <- mammographic_masses %>%
    mutate(mammographic_masses[[,i]] ="
>     mutate(mammographic_masses[[,i]] = replace(mammographic_masses[[,i]], mammographic_masses[[,i]] == "N/A", NA))
Error: unexpected '=' in "    mutate(mammographic_masses[[,i]] ="
> }
Error: unexpected '}' in "}"

我也在阅读其他方式，如应用等，但我想不出一种方法来循环每列

4

3 回答 3

1

提供“新”dplyr首选across以及str_replace_all（好点@Gregor）

library(dplyr)
library(stringr)


mammographic_masses %>%
  mutate(across(everything(), 
         ~ str_replace_all(., c("na" = NA_character_, "N/A" = NA_character_))))

#>      V1   V2   V3   V4
#> 1     d    b <NA>    c
#> 2     d    b <NA> <NA>
#> 3  <NA> <NA>    d    b
#> 4     a <NA> <NA>    b
#> 5     a    b    d <NA>
#> 6     d    c    b    c
#> 7     b    b    d <NA>
#> 8  <NA> <NA> <NA>    d
#> 9     a    d    d <NA>
#> 10 <NA>    b    d <NA>

与锐相同的数据

set.seed(2020)
n <- 10
mammographic_masses <- replicate(4, sample(c(letters[1:4], "na", "N/A"), n, TRUE))
mammographic_masses <- as.data.frame(mammographic_masses)
于 2020-06-02T17:00:18.337 回答
1

而不是循环，使用mutate_all.

library(dplyr)

mammographic_masses %>%
  mutate_all(function(x) {is.na(x) <- x %in% c("na", "N/A"); x})
#     V1   V2   V3   V4
#1     d    b <NA>    c
#2     d    b <NA> <NA>
#3  <NA> <NA>    d    b
#4     a <NA> <NA>    b
#5     a    b    d <NA>
#6     d    c    b    c
#7     b    b    d <NA>
#8  <NA> <NA> <NA>    d
#9     a    d    d <NA>
#10 <NA>    b    d <NA>

测试数据创建代码

set.seed(2020)
n <- 10
mammographic_masses <- replicate(4, sample(c(letters[1:4], "na", "N/A"), n, TRUE))
mammographic_masses <- as.data.frame(mammographic_masses)
于 2020-06-02T15:58:37.393 回答
0

我们也可以使用na_if

library(dplyr)
mammographic_masses %>%
     mutate(across(everything(), ~ na_if(na_if(., "na"), "N/A")))

数据

set.seed(2020)
n <- 10
mammographic_masses <- replicate(4, sample(c(letters[1:4], "na", "N/A"), n, TRUE))
mammographic_masses <- as.data.frame(mammographic_masses)
于 2020-06-02T19:20:22.380 回答