r - 使用 data.table 提取行中的最后一个非缺失值

Question

我有一个因子列的 data.table，我想提取每行中最后一个非缺失值的标签。这是一种典型的max.col情况，但我不想不必要地强制，因为我正在尝试使用 data.table 优化此代码。真实数据也有其他类型的列。

这是例子，

## Some sample data
set.seed(0)
dat <- sapply(split(letters[1:25], rep.int(1:5, 5)), sample, size=8, replace=TRUE)
dat[upper.tri(dat)] <- NA
dat[4:5, 4:5] <- NA                              # the real data isnt nice and upper.triangular
dat <- data.frame(dat, stringsAsFactors = TRUE)  # factor columns

## So, it looks like this
setDT(dat)[]
#    X1 X2 X3 X4 X5
# 1:  u NA NA NA NA
# 2:  f  q NA NA NA
# 3:  f  b  w NA NA
# 4:  k  g  h NA NA
# 5:  u  b  r NA NA
# 6:  f  q  w  x  t
# 7:  u  g  h  i  e
# 8:  u  q  r  n  t

## I just want to get the labels of the factors
## that are 'rightmost' in each row.  I tried a number of things 
## that probably don't make sense here.
## This just about gets the column index
dat[, colInd := sum(!is.na(.SD)), by=1:nrow(dat)]

不过，这是提取这些标签的目标，这里使用常规基本函数。

## Using max.col and a data.frame
df1 <- as.data.frame(dat)
inds <- max.col(is.na(as.matrix(df1)), ties="first")-1
inds[inds==0] <- ncol(df1)
df1[cbind(1:nrow(df1), inds)]
# [1] "u" "q" "w" "h" "r" "t" "e" "t"

Answer 1

这是另一种方式:

dat[, res := NA_character_]
for (v in rev(names(dat))[-1]) dat[is.na(res), res := get(v)]


   X1 X2 X3 X4 X5 res
1:  u NA NA NA NA   u
2:  f  q NA NA NA   q
3:  f  b  w NA NA   w
4:  k  g  h NA NA   h
5:  u  b  r NA NA   r
6:  f  q  w  x  t   t
7:  u  g  h  i  e   e
8:  u  q  r  n  t   t

基准 使用与@alexis_laz 相同的数据并对函数进行(显然)表面上的更改，我看到了不同的结果。只是在这里展示它们以防万一有人好奇。亚历克西斯的答案(稍作修改)仍然领先。

职能:

alex = function(x, ans = rep_len(NA, length(x[[1L]])), wh = seq_len(length(x[[1L]]))){
    if(!length(wh)) return(ans)
    ans[wh] = as.character(x[[length(x)]])[wh]
    Recall(x[-length(x)], ans, wh[is.na(ans[wh])])
}   

alex2 = function(x){
    x[, res := NA_character_]
    wh = x[, .I]
    for (v in (length(x)-1):1){
      if (!length(wh)) break
      set(x, j="res", i=wh, v = x[[v]][wh])
      wh = wh[is.na(x$res[wh])]
    }
    x$res
}

frank = function(x){
    x[, res := NA_character_]
    for(v in rev(names(x))[-1]) x[is.na(res), res := get(v)]
    return(x$res)       
}

frank2 = function(x){
    x[, res := NA_character_]
    for(v in rev(names(x))[-1]) x[is.na(res), res := .SD, .SDcols=v]
    x$res
}

示例数据和基准:

DAT1 = as.data.table(lapply(ceiling(seq(0, 1e4, length.out = 1e2)), 
                     function(n) c(rep(NA, n), sample(letters, 3e5 - n, TRUE))))
DAT2 = copy(DAT1)
DAT3 = as.list(copy(DAT1))
DAT4 = copy(DAT1)

library(microbenchmark)
microbenchmark(frank(DAT1), frank2(DAT2), alex(DAT3), alex2(DAT4), times = 30)

Unit: milliseconds
         expr       min        lq      mean    median         uq        max neval
  frank(DAT1) 850.05980 909.28314 985.71700 979.84230 1023.57049 1183.37898    30
 frank2(DAT2)  88.68229  93.40476 118.27959 107.69190  121.60257  346.48264    30
   alex(DAT3)  98.56861 109.36653 131.21195 131.20760  149.99347  183.43918    30
  alex2(DAT4)  26.14104  26.45840  30.79294  26.67951   31.24136   50.66723    30