rbindfill 像向量列表的合并

Question

我有一个命名向量列表(见下文和结尾 dput 版本)如果向量不包含名称(在这种情况下为字符)，我想“合并”在一起以创建矩阵并填充零.这似乎并不难，但我还没有找到 工作基地解决方案到问题。我考虑过使用 match，但当我确定有一种奇特的方式来使用时，这似乎非常耗费时间 do.call和 rbind一起。

命名向量列表:

$greg

e i k l 
1 2 1 1 

$sam

! c e i t 
1 1 1 2 1 

$teacher

? c i k l 
1 1 1 1 1 

最终期望输出

           !  ?  c  e  i  k  l  t
greg       0  0  0  1  2  1  1  0 
sam        1  0  1  1  2  0  0  1 
teacher    0  1  1  0  1  1  1  0 

可能这是人们会给出的输出，用 0 填充 NA 很容易

           !  ?  c  e  i  k  l  t
greg      NA NA NA  1  2  1  1 NA 
sam        1 NA  1  1  2 NA NA  1 
teacher   NA  1  1 NA  1  1  1 NA 

样本数据

L2 <- structure(list(greg = structure(c(1L, 2L, 1L, 1L), .Dim = 4L, .Dimnames = structure(list(
        c("e", "i", "k", "l")), .Names = ""), class = "table"), sam = structure(c(1L, 
    1L, 1L, 2L, 1L), .Dim = 5L, .Dimnames = structure(list(c("!", 
    "c", "e", "i", "t")), .Names = ""), class = "table"), teacher = structure(c(1L, 
    1L, 1L, 1L, 1L), .Dim = 5L, .Dimnames = structure(list(c("?", 
    "c", "i", "k", "l")), .Names = ""), class = "table")), .Names = c("greg", 
    "sam", "teacher"))

Answer 1

这是一个相当直接的基本解决方案:

# first determine all possible column names
cols <- sort(unique(unlist(lapply(L2,names), use.names=FALSE)))
# initialize the output
out <- matrix(0, length(L2), length(cols), dimnames=list(names(L2),cols))
# loop over list and fill in the matrix
for(i in seq_along(L2)) {
  out[names(L2)[i], names(L2[[i]])] <- L2[[i]]
}

使用基准更新:

f1 <- function(L2) {
  cols <- sort(unique(unlist(lapply(L2,names), use.names=FALSE)))
  out <- matrix(0, length(L2), length(cols), dimnames=list(names(L2),cols))
  for(i in seq_along(L2)) out[names(L2)[i], names(L2[[i]])] <- L2[[i]]
  out
}   
f2 <- function(L2) {
  L.names <- sort(unique(unlist(sapply(L2, names))))
  L3 <- t(sapply(L2, function(x) x[L.names]))
  colnames(L3) <- L.names
  L3[is.na(L3)] <- 0
  L3
}
f3 <- function(L2) {
  m <- do.call(rbind, lapply(L2, as.data.frame))
  m$row <- sub("[.].*", "", rownames(m))
  m$Var1 <- factor(as.character(m$Var1))
  xtabs(Freq ~ row + Var1, m)
}
library(rbenchmark)
benchmark(f1(L2), f2(L2), f3(L2), order="relative")[,1:5]
#     test replications elapsed relative user.self
# 1 f1(L2)          100   0.022    1.000     0.020
# 2 f2(L2)          100   0.051    2.318     0.052
# 3 f3(L2)          100   0.788   35.818     0.760
set.seed(21)
L <- replicate(676, {n=sample(10,1); l=sample(26,n);
  setNames(sample(6,n,TRUE), letters[l])}, simplify=FALSE)
names(L) <- levels(interaction(letters,LETTERS))
benchmark(f1(L), f2(L), order="relative")[,1:5]
#    test replications elapsed relative user.self
# 1 f1(L)          100    1.84    1.000     1.828
# 2 f2(L)          100    4.24    2.304     4.220