若干备选方案：

1）data.table的两种方式：

library(data.table)
# method 1 (preferred)
setDT(v)[, lapply(.SD, function(x) unlist(tstrsplit(x, ",", fixed=TRUE))), by = AB
         ][!is.na(director)]
# method 2
setDT(v)[, strsplit(as.character(director), ",", fixed=TRUE), by = .(AB, director)
         ][,.(director = V1, AB)]

2）dplyr/tidyr组合：

library(dplyr)
library(tidyr)
v %>% 
  mutate(director = strsplit(as.character(director), ",")) %>%
  unnest(director)

**3）仅限tidyr：**对于tidyr 0.5.0（及更高版本），您也可以仅使用separate_rows：

separate_rows(v, director, sep = ",")

可以使用convert = TRUE参数将数字自动转换为数值列。
使用tidyr_1.3.0（及更高版本），您可以使用separate_longer_delim（现在已取代separate_rows）：

separate_longer_delim(v, director, delim = ",")

4）具有碱R：

# if 'director' is a character-column:
stack(setNames(strsplit(df$director,','), df$AB))

# if 'director' is a factor-column:
stack(setNames(strsplit(as.character(df$director),','), df$AB))

这个老问题经常被用作欺骗目标（标记为r-faq）。到今天为止，已经回答了三次，提供了6种不同的方法，但是缺乏一个基准作为指导，哪种方法是最快的1。
基准解决方案包括

• Matthew Lundberg's base R approach，但根据Rich Scriven的评论进行了修改，
• Jaap's两种data.table方法和两种dplyr/tidyr方法，
• Ananda's splitstackshape solution，
• 以及Jaap的data.table方法的两个附加变体。

使用microbenchmark包，在6种不同大小的 Dataframe 上对8种不同的方法进行了基准测试（参见下面的代码）。
OP给出的样本数据仅由20行组成。为了创建更大的 Dataframe ，这20行简单地重复1、10、100、1000、10000和100000次，这给予了高达200万行的问题大小。

基准测试结果

基准测试结果表明，对于足够大的 Dataframe ，所有data.table方法都比任何其他方法更快。对于超过5000行的 Dataframe ，Jaap的data.table方法2和变体DT3是最快的，比最慢的方法快了很多。
值得注意的是，两种tidyverse方法和splistackshape解决方案的时间非常相似，以至于很难区分图表中的曲线。它们是所有 Dataframe 大小的基准方法中最慢的。
对于较小的 Dataframe ，Matt的基本R解决方案和data.table方法4似乎比其他方法具有更少的开销。

代码

director <- 
  c("Aaron Blaise,Bob Walker", "Akira Kurosawa", "Alan J. Pakula", 
    "Alan Parker", "Alejandro Amenabar", "Alejandro Gonzalez Inarritu", 
    "Alejandro Gonzalez Inarritu,Benicio Del Toro", "Alejandro González Iñárritu", 
    "Alex Proyas", "Alexander Hall", "Alfonso Cuaron", "Alfred Hitchcock", 
    "Anatole Litvak", "Andrew Adamson,Marilyn Fox", "Andrew Dominik", 
    "Andrew Stanton", "Andrew Stanton,Lee Unkrich", "Angelina Jolie,John Stevenson", 
    "Anne Fontaine", "Anthony Harvey")
AB <- c("A", "B", "A", "A", "B", "B", "B", "A", "B", "A", "B", "A", 
        "A", "B", "B", "B", "B", "B", "B", "A")

library(data.table)
library(magrittr)

为问题大小为n的benchmark运行定义函数

run_mb <- function(n) {
  # compute number of benchmark runs depending on problem size `n`
  mb_times <- scales::squish(10000L / n , c(3L, 100L)) 
  cat(n, " ", mb_times, "\n")
  # create data
  DF <- data.frame(director = rep(director, n), AB = rep(AB, n))
  DT <- as.data.table(DF)
  # start benchmarks
  microbenchmark::microbenchmark(
    matt_mod = {
      s <- strsplit(as.character(DF$director), ',')
      data.frame(director=unlist(s), AB=rep(DF$AB, lengths(s)))},
    jaap_DT1 = {
      DT[, lapply(.SD, function(x) unlist(tstrsplit(x, ",", fixed=TRUE))), by = AB
         ][!is.na(director)]},
    jaap_DT2 = {
      DT[, strsplit(as.character(director), ",", fixed=TRUE), 
         by = .(AB, director)][,.(director = V1, AB)]},
    jaap_dplyr = {
      DF %>% 
        dplyr::mutate(director = strsplit(as.character(director), ",")) %>%
        tidyr::unnest(director)},
    jaap_tidyr = {
      tidyr::separate_rows(DF, director, sep = ",")},
    cSplit = {
      splitstackshape::cSplit(DF, "director", ",", direction = "long")},
    DT3 = {
      DT[, strsplit(as.character(director), ",", fixed=TRUE),
         by = .(AB, director)][, director := NULL][
           , setnames(.SD, "V1", "director")]},
    DT4 = {
      DT[, .(director = unlist(strsplit(as.character(director), ",", fixed = TRUE))), 
         by = .(AB)]},
    times = mb_times
  )
}

针对不同问题大小运行基准测试

# define vector of problem sizes
n_rep <- 10L^(0:5)
# run benchmark for different problem sizes
mb <- lapply(n_rep, run_mb)

准备出图数据

mbl <- rbindlist(mb, idcol = "N")
mbl[, n_row := NROW(director) * n_rep[N]]
mba <- mbl[, .(median_time = median(time), N = .N), by = .(n_row, expr)]
mba[, expr := forcats::fct_reorder(expr, -median_time)]

创建图表

library(ggplot2)
ggplot(mba, aes(n_row, median_time*1e-6, group = expr, colour = expr)) + 
  geom_point() + geom_smooth(se = FALSE) + 
  scale_x_log10(breaks = NROW(director) * n_rep) + scale_y_log10() + 
  xlab("number of rows") + ylab("median of execution time [ms]") +
  ggtitle("microbenchmark results") + theme_bw()

Session信息和包版本（节选）

devtools::session_info()
#Session info
# version  R version 3.3.2 (2016-10-31)
# system   x86_64, mingw32
#Packages
# data.table      * 1.10.4  2017-02-01 CRAN (R 3.3.2)
# dplyr             0.5.0   2016-06-24 CRAN (R 3.3.1)
# forcats           0.2.0   2017-01-23 CRAN (R 3.3.2)
# ggplot2         * 2.2.1   2016-12-30 CRAN (R 3.3.2)
# magrittr        * 1.5     2014-11-22 CRAN (R 3.3.0)
# microbenchmark    1.4-2.1 2015-11-25 CRAN (R 3.3.3)
# scales            0.4.1   2016-11-09 CRAN (R 3.3.2)
# splitstackshape   1.4.2   2014-10-23 CRAN (R 3.3.3)
# tidyr             0.6.1   2017-01-10 CRAN (R 3.3.2)

1我的好奇心被这番热情洋溢的评论激起了 * 太棒了！数量级更快！* 到a question的tidyverse答案，该答案作为此问题的重复而关闭。

命名你的原始数据.frame v，我们有：

> s <- strsplit(as.character(v$director), ',')
> data.frame(director=unlist(s), AB=rep(v$AB, sapply(s, FUN=length)))
                      director AB
1                 Aaron Blaise  A
2                   Bob Walker  A
3               Akira Kurosawa  B
4               Alan J. Pakula  A
5                  Alan Parker  A
6           Alejandro Amenabar  B
7  Alejandro Gonzalez Inarritu  B
8  Alejandro Gonzalez Inarritu  B
9             Benicio Del Toro  B
10 Alejandro González Iñárritu  A
11                 Alex Proyas  B
12              Alexander Hall  A
13              Alfonso Cuaron  B
14            Alfred Hitchcock  A
15              Anatole Litvak  A
16              Andrew Adamson  B
17                 Marilyn Fox  B
18              Andrew Dominik  B
19              Andrew Stanton  B
20              Andrew Stanton  B
21                 Lee Unkrich  B
22              Angelina Jolie  B
23              John Stevenson  B
24               Anne Fontaine  B
25              Anthony Harvey  A

注意使用rep构建新的AB列。在这里，sapply返回每个原始行中的名称数。

虽然有些晚了，但另一个通用的替代方案是使用我的“splitstackshape”包中的cSplit，它有一个direction参数。将其设置为"long"以获得指定的结果：

library(splitstackshape)
head(cSplit(mydf, "director", ",", direction = "long"))
#              director AB
# 1:       Aaron Blaise  A
# 2:         Bob Walker  A
# 3:     Akira Kurosawa  B
# 4:     Alan J. Pakula  A
# 5:        Alan Parker  A
# 6: Alejandro Amenabar  B

devtools::install_github("yikeshu0611/onetree")

library(onetree)

dd=spread_byonecolumn(data=mydata,bycolumn="director",joint=",")

head(dd)
            director AB
1       Aaron Blaise  A
2         Bob Walker  A
3     Akira Kurosawa  B
4     Alan J. Pakula  A
5        Alan Parker  A
6 Alejandro Amenabar  B

另一个使用strsplit从 base 得到的基准测试目前可以推荐 * 将一列中的逗号分隔字符串拆分为单独的行 *，因为它在各种大小范围内都是最快的：

s <- strsplit(v$director, ",", fixed=TRUE)
s <- data.frame(director=unlist(s), AB=rep(v$AB, lengths(s)))

请注意，使用fixed=TRUE对计时有很大影响。

比较方法：

met <- alist(base = {s <- strsplit(v$director, ",") #Matthew Lundberg
   s <- data.frame(director=unlist(s), AB=rep(v$AB, sapply(s, FUN=length)))}
 , baseLength = {s <- strsplit(v$director, ",") #Rich Scriven
   s <- data.frame(director=unlist(s), AB=rep(v$AB, lengths(s)))}
 , baseLeFix = {s <- strsplit(v$director, ",", fixed=TRUE)
   s <- data.frame(director=unlist(s), AB=rep(v$AB, lengths(s)))}
 , cSplit = s <- cSplit(v, "director", ",", direction = "long") #A5C1D2H2I1M1N2O1R2T1
 , dt = s <- setDT(v)[, lapply(.SD, function(x) unlist(tstrsplit(x, "," #Jaap
   , fixed=TRUE))), by = AB][!is.na(director)]
#, dt2 = s <- setDT(v)[, strsplit(director, "," #Jaap #Only Unique
#  , fixed=TRUE), by = .(AB, director)][,.(director = V1, AB)]
 , dplyr = {s <- v %>%  #Jaap
    mutate(director = strsplit(director, ",", fixed=TRUE)) %>%
    unnest(director)}
 , tidyr = s <- separate_rows(v, director, sep = ",") #Jaap
 , stack = s <- stack(setNames(strsplit(v$director, ",", fixed=TRUE), v$AB)) #Jaap
#, dt3 = {s <- setDT(v)[, strsplit(director, ",", fixed=TRUE), #Uwe #Only Unique
#  by = .(AB, director)][, director := NULL][, setnames(.SD, "V1", "director")]}
 , dt4 = {s <- setDT(v)[, .(director = unlist(strsplit(director, "," #Uwe
   , fixed = TRUE))), by = .(AB)]}
 , dt5 = {s <- vT[, .(director = unlist(strsplit(director, "," #Uwe
   , fixed = TRUE))), by = .(AB)]}
   )

图书馆：

library(microbenchmark)
library(splitstackshape) #cSplit
library(data.table) #dt, dt2, dt3, dt4
#setDTthreads(1) #Looks like it has here minor effect
library(dplyr) #dplyr
library(tidyr) #dplyr, tidyr

数据：

v0 <- data.frame(director = c("Aaron Blaise,Bob Walker", "Akira Kurosawa", 
                        "Alan J. Pakula", "Alan Parker", "Alejandro Amenabar", "Alejandro Gonzalez Inarritu", 
                        "Alejandro Gonzalez Inarritu,Benicio Del Toro", "Alejandro González Iñárritu", 
                        "Alex Proyas", "Alexander Hall", "Alfonso Cuaron", "Alfred Hitchcock", 
                        "Anatole Litvak", "Andrew Adamson,Marilyn Fox", "Andrew Dominik", 
                        "Andrew Stanton", "Andrew Stanton,Lee Unkrich", "Angelina Jolie,John Stevenson", 
                        "Anne Fontaine", "Anthony Harvey"), AB = c('A', 'B', 'A', 'A', 'B', 'B', 'B', 'A', 'B', 'A', 'B', 'A', 'A', 'B', 'B', 'B', 'B', 'B', 'B', 'A'))

计算和计时结果：

n <- 10^(0:5)
x <- lapply(n, function(n) {v <- v0[rep(seq_len(nrow(v0)), n),]
  vT <- setDT(v)
  ti <- min(100, max(3, 1e4/n))
  microbenchmark(list = met, times = ti, control=list(order="block"))})

y <- do.call(cbind, lapply(x, function(y) aggregate(time ~ expr, y, median)))
y <- cbind(y[1], y[-1][c(TRUE, FALSE)])
y[-1] <- y[-1] / 1e6 #ms
names(y)[-1] <- paste("n:", n * nrow(v0))
y #Time in ms
#         expr     n: 20    n: 200    n: 2000   n: 20000   n: 2e+05   n: 2e+06
#1        base 0.2989945 0.6002820  4.8751170  46.270246  455.89578  4508.1646
#2  baseLength 0.2754675 0.5278900  3.8066300  37.131410  442.96475  3066.8275
#3   baseLeFix 0.2160340 0.2424550  0.6674545   4.745179   52.11997   555.8610
#4      cSplit 1.7350820 2.5329525 11.6978975  99.060448 1053.53698 11338.9942
#5          dt 0.7777790 0.8420540  1.6112620   8.724586  114.22840  1037.9405
#6       dplyr 6.2425970 7.9942780 35.1920280 334.924354 4589.99796 38187.5967
#7       tidyr 4.0323765 4.5933730 14.7568235 119.790239 1294.26959 11764.1592
#8       stack 0.2931135 0.4672095  2.2264155  22.426373  289.44488  2145.8174
#9         dt4 0.5822910 0.6414900  1.2214470   6.816942   70.20041   787.9639
#10        dt5 0.5015235 0.5621240  1.1329110   6.625901   82.80803   636.1899

注意，方法如

(v <- rbind(v0[1:2,], v0[1,]))
#                 director AB
#1 Aaron Blaise,Bob Walker  A
#2          Akira Kurosawa  B
#3 Aaron Blaise,Bob Walker  A

setDT(v)[, strsplit(director, "," #Jaap #Only Unique
  , fixed=TRUE), by = .(AB, director)][,.(director = V1, AB)]
#         director AB
#1:   Aaron Blaise  A
#2:     Bob Walker  A
#3: Akira Kurosawa  B

为uniquedirector 返回strsplit，可能与

tmp <- unique(v)
s <- strsplit(tmp$director, ",", fixed=TRUE)
s <- data.frame(director=unlist(s), AB=rep(tmp$AB, lengths(s)))

但据我所知，当局并没有提出这项要求。