r - 顶级类别的一个热编码，NA，其余的归入 R 中的 'others'

Question

我只想对顶级类别、NA 和“其他”的变量进行一次热编码。

所以在这个简化的例子中，热编码 b where freq > 1 and NA:

id <- c(1, 2, 3, 4, 5, 6)
b <- c(NA, "A", "C", "A", "B", "C")
c <- c(2, 3, 6, NA, 4, 7)
df <- data.frame(id, b, c)

  id    b  c
1  1 <NA>  2
2  2    A  3
3  3    C  6
4  4    A NA
5  5    B  4
6  6    C  7

table <- as.data.frame(table(df$b))

  Var1 Freq
1    A    2
2    B    1
3    C    2

table_top <- table[table$Freq > 1,]

  Var1 Freq
1    A    2
3    C    2

现在，我想要这样的东西

  id  b_NA  c b_A b_C b_Others
    1    1  2   0   0        0
    2    0  3   1   0        0
    3    0  6   0   1        0
    4    0 NA   1   0        0
    5    0  4   0   0        1
    6    0  7   0   1        0

我试过子集 df

table_top <- as.vector(table_top$Var1)
table_only_top <- subset(df, b %in% table_top)
table_only_top

  a b  c
2 1 A  3
3 2 C  6
4 2 A NA
6 3 C  7

但是，现在我不知道如何获得输出。在我的真实数据中，我的类别比此处多得多，因此无法使用输出中的名称。我的实际输出中的其他类别也存在许多类别。

非常感谢任何提示:)

Answer 1

data.table 和 mltools 快速而性感:

> one_hot(dt, naCols = TRUE, sparsifyNAs = TRUE)

   id cat_NA cat_A cat_C cat_Others freq
1:  1      1     0     0          0    2
2:  2      0     1     0          0    3
3:  3      0     0     1          0    6
4:  4      0     1     0          0   NA
5:  5      0     0     0          1    4
6:  6      0     0     1          0    7

代码

加载库

library(dplyr)
library(data.table)
library(mltools)

转换数据

# Kick out all with freq == 1 and below
df <- df %>%
    # Group by variables that will be onehotted
    group_by(cat) %>%
    # Add a count per group item column 
    mutate(count = n()) %>%
    # Ungroup for next steps
    ungroup() %>%
    # Change all that have a count of 1 or below to "Others".
    # If cat was a factor, we would get numeric results at this step.
    mutate(cat = ifelse(!is.na(cat) & count <= 1, "Others", cat),
    # Only now we turn it into a factor for the one_hot function 
                        cat = as.factor(cat)) %>%
    # Drop the count column
    select(id, cat, freq)

# Turn into data.table
dt <- as.data.table(df)

检查中间结果

> dt
       id    cat freq
1:  1   <NA>    2
2:  2      A    3
3:  3      C    6
4:  4      A   NA
5:  5 Others    4
6:  6      C    7

数据

id <- c(1, 2, 3, 4, 5, 6)
cat <- c(NA, "A", "C", "A", "B", "C")
freq <- c(2, 3, 6, NA, 4, 7)
# It is important to have no other factor variables other
# than the variable(s) you one want to one hot. For that reason
# the automatic factoring is turned off.
df <- data.frame(id, cat, freq, 
                 stringsAsFactors = FALSE)          

> df
  id  cat freq
1  1 <NA>    2
2  2    A    3
3  3    C    6
4  4    A   NA
5  5    B    4
6  6    C    7