Question

我有一个包含向量作为值的列的数据框。现在我需要通过对矢量进行解包来拉伸这个数据帧。

看一下这个例子：

df <- structure(list(id = c(1, 1, 1, 1, 1, 2, 2, 2, 2, 2), id2 = c(1, 
2, 3, 4, 5, 1, 2, 3, 4, 5), value = c("1", "2", "3", "c(1,3,4)", 
"1:5", "1", "2", "3", "1:4", "2:4")), .Names = c("id", "id2", 
"value"), row.names = c(NA, 10L), class = "data.frame")
df
   id id2    value
1   1   1        1
2   1   2        2
3   1   3        3
4   1   4 c(1,3,4)
5   1   5      1:5
6   2   1        1
7   2   2        2
8   2   3        3
9   2   4      1:4
10  2   5      2:4

this has to be changed into:

df2 <- structure(list(id = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), id2 = c(1L, 2L, 
3L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 1L, 2L, 3L, 4L, 4L, 4L, 4L, 
5L, 5L, 5L), value = c(1L, 2L, 3L, 1L, 3L, 4L, 1L, 2L, 3L, 4L, 
5L, 1L, 2L, 3L, 1L, 2L, 3L, 4L, 2L, 3L, 4L)), .Names = c("id", 
"id2", "value"), class = "data.frame", row.names = c(NA, -21L
))

df2
   id id2 value
1   1   1     1
2   1   2     2
3   1   3     3
4   1   4     1
5   1   4     3
6   1   4     4
7   1   5     1
8   1   5     2
9   1   5     3
10  1   5     4
11  1   5     5
12  2   1     1
13  2   2     2
14  2   3     3
15  2   4     1
16  2   4     2
17  2   4     3
18  2   4     4
19  2   5     2
20  2   5     3
21  2   5     4

所以这是一种不同类型的将宽格式转换为长格式而不是我们习惯于使用例如reshape2包。有没有人有解决这个问题的方法？

*编辑

我忘了提到一些值实际上是这样的字符值：

df <- structure(list(id = c(1, 1, 1, 1, 1, 2, 2, 2, 2, 2), id2 = c(1, 
2, 3, 4, 5, 1, 2, 3, 4, 5), value = c("1", "2", "Hi", "c(1,3,4)", 
"1:5", "1", "2", "hello", "1:4", "2:4")), .Names = c("id", "id2", 
"value"), row.names = c(NA, 10L), class = "data.frame")
df
   id id2    value
1   1   1        1
2   1   2        2
3   1   3       Hi
4   1   4 c(1,3,4)
5   1   5      1:5
6   2   1        1
7   2   2        2
8   2   3    hello
9   2   4      1:4
10  2   5      2:4

Answer 1

同样使用data.table

的单行班次

library(data.table)
setDT(df)[, as.integer(eval.parent(parse(text = value))), by = .(id, id2)]
#     id id2 V1
#  1:  1   1  1
#  2:  1   2  2
#  3:  1   3  3
#  4:  1   4  1
#  5:  1   4  3
#  6:  1   4  4
#  7:  1   5  1
#  8:  1   5  2
#  9:  1   5  3
# 10:  1   5  4
# 11:  1   5  5
# 12:  2   1  1
# 13:  2   2  2
# 14:  2   3  3
# 15:  2   4  1
# 16:  2   4  2
# 17:  2   4  3
# 18:  2   4  4
# 19:  2   5  2
# 20:  2   5  3
# 21:  2   5  4

Answer 2

你可以做到

df$value <- lapply(df$value, function(x) {
  res <- try(eval(parse(text=x)), silent=T)
  if (!inherits(res, "try-error")) as.character(res) else x
})
# install.packages("tidyr") # uncomment and run if needed
tidyr::unnest(df)
# Source: local data frame [21 x 3]
# 
#       id   id2 value
#    (dbl) (dbl) (chr)
# 1      1     1     1
# 2      1     2     2
# 3      1     3    Hi
# 4      1     4     1
# 5      1     4     3
# 6      1     4     4
# 7      1     5     1
# 8      1     5     2
# 9      1     5     3
# 10     1     5     4
# ..   ...   ...   ...

但是，这可能不是最优雅的选择。

如何通过对包含r中的向量的列进行分解来拉伸数据框？

2 个答案: