Question

我想创建一个新列，其中每个值都是我数据中该行的其他值的随机子集。

# Example data:
df <- data.frame(matrix(nrow = 57, ncol = 6)) %>% 
  mutate(
    X1 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X2 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X3 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X4 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X5 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X6 = round(rnorm(n = 57, mean = 0, sd = 1), 1)
  )

# my failed attempt at a new column
df %>% 
  rowwise() %>% 
  mutate(X7 = str_c(df[, sample(1:6, 3, replace = F)]), sep = ", ")

Answer 1

解决方案使用tidyverse。关键是逐行拆分数据并应用函数来对每个行子集的值进行采样。 map_df可以实现上述任务并将所有输出组合到数据帧。 df2是最终输出。

# Load package
library(tidyverse)

# Set seed
set.seed(123)

# Create example data frame
df <- data.frame(matrix(nrow = 57, ncol = 6)) %>% 
  mutate(
    X1 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X2 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X3 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X4 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X5 = round(rnorm(n = 57, mean = 0, sd = 1), 1),
    X6 = round(rnorm(n = 57, mean = 0, sd = 1), 1)
  )

# Process the data
df2 <- df %>%
  rowid_to_column() %>%
  split(f = .$rowid) %>%
  map_df(function(dt){
    dt_sub <- dt %>% 
      select(-rowid) %>%
      select(sample(1:6, 3, replace = FALSE)) %>%
      unite(X7, everything(), sep = ", ")
    return(dt_sub)
  }) %>%
  bind_cols(df) %>%
  select(paste0("X", 1:7))

df2
     X1   X2   X3   X4   X5   X6               X7
1  -0.6  0.6  0.5  0.1  0.9  0.1    0.1, 0.5, 0.9
2  -0.2  0.1  0.3  0.0 -1.0  0.2    0.1, 0.3, 0.2
3   1.6  0.2  0.1  2.1  2.0  1.6    1.6, 2.1, 0.1
4   0.1  0.4 -0.6 -0.7 -0.1 -0.2   0.1, 0.4, -0.6
5   0.1 -0.5 -0.8 -1.1  0.2  0.2   0.1, 0.2, -0.5
6   1.7 -0.3 -1.0  0.0 -0.7  1.2   -1, -0.7, -0.3
7   0.5 -1.0  0.1  0.3 -0.6  1.1    0.5, -0.6, -1
...

Answer 2

我认为最好的方法是使用基础R函数replicate，sample和sapply。

inx <- t(replicate(nrow(df), sample(1:6, 3, replace = F)))
df$X7 <- sapply(seq_len(nrow(df)), function(i)
            paste(df[i, inx[i, ]], collapse = ", "))

Answer 3

这是dplyr中的解决方案：

library(dplyr)

df %>%
  group_by(idx = seq(n())) %>%
  do({
    res <- select(., -idx)
    bind_cols(res, X7 = toString(sample(unlist(res),
                                        3, replace = FALSE)))
  }) %>%
  ungroup() %>%
  select(-idx)

结果：

# A tibble: 57 x 7
      X1    X2    X3    X4    X5    X6              X7
   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>           <chr>
 1   0.4   0.4  -0.1   3.4   0.9  -0.4   0.4, 0.9, 0.4
 2   1.5   0.9  -0.7   1.5  -1.1  -0.3 -0.7, 1.5, -1.1
 3  -0.1  -0.5  -0.6  -0.8  -0.3   2.3 -0.3, 2.3, -0.8
 4   0.7  -1.0   0.3   0.2  -0.5  -0.3   -1, 0.3, -0.3
 5   0.6   0.9   0.4   1.9  -0.7  -2.0    0.4, -2, 0.9
 6   0.3   0.7   1.3   0.6   1.3  -0.2  0.7, -0.2, 1.3
 7   0.5   0.3   1.1  -0.2  -0.4  -0.8   0.5, 1.1, 0.3
 8   0.4  -1.9   0.8  -0.6  -1.1   0.4 0.4, -1.9, -0.6
 9   0.2  -1.5  -1.9   1.0   0.0   0.6       0, 1, 0.6
10  -0.2   0.7  -0.5   1.4   0.3  -0.1 -0.2, 0.3, -0.5

创建新列，该列是其他列的随机子集

3 个答案: