Question

我有一个如下数据框。

    A  B C
V1  a  1 e
V2  b  2 f
V3  c  3 g,h,i
V4  d  4 j,k

C列中的数据类是列表。

我想取消列C列数据并在数据帧中生成多行，如下所示。

    A  B C
V1  a  1 e
V2  b  2 f
V3  c  3 g
V4  c  3 h
V5  c  3 i
V6  d  4 j
V7  d  4 k

怎么做？

非常感谢。

Answer 1

我们可以使用cSplit

library(splitstackshape)
cSplit(df1, "C", sep=",", "long")
#   A B C
#1: a 1 e
#2: b 2 f
#3: c 3 g
#4: c 3 h
#5: c 3 i
#6: d 4 j
#7: d 4 k

或使用unnest

中的tidyr

library(tidyr)
unnest(df1, C=strsplit(C, ","))
#  A B C
#1 a 1 e
#2 b 2 f
#3 c 3 g
#4 c 3 h
#5 c 3 i
#6 d 4 j
#7 d 4 k

或base R

lst <- strsplit(df1$C, ",")
transform(df1[rep(1:nrow(df1), lengths(lst)),-3], C= unlist(lst))
#     A B C
#V1   a 1 e
#V2   b 2 f
#V3   c 3 g
#V3.1 c 3 h
#V3.2 c 3 i
#V4   d 4 j
#V4.1 d 4 k

注意：如果＆＃34; C＆＃34;列为factor，转换为character并在strsplit中使用，即strsplit(as.character(df1$C), ",")

更新

假设列是＆＃34; C＆＃34;是list，我们仍然可以使用unnest

unnest(df2, C)
#  A B C
#1 a 1 e
#2 b 2 f
#3 c 3 g
#4 c 3 h
#5 c 3 i
#6 d 4 j
#7 d 4 k

或listCol_l

中的splitstackshape

listCol_l(df2, "C")[]

数据

df1 <- structure(list(A = c("a", "b", "c", "d"), B = 1:4, C = c("e", 
"f", "g,h,i", "j,k")), .Names = c("A", "B", "C"), 
class = "data.frame",   row.names = c("V1", "V2", "V3", "V4"))

df2 <- structure(list(A = c("a", "b", "c", "d"), B = 1:4, C = list("e", 
"f", c("g", "h", "i"), c("j", "k"))), .Names = c("A", "B", 
"C"), row.names = c("V1", "V2", "V3", "V4"), class = "data.frame")

Answer 2

使用：

s <- strsplit(df$C, split = ",")
data.frame(A = rep(df$A, sapply(s, length)), C = unlist(s))

R - 使多个元素列表到数据帧行

2 个答案:

更新

数据