下面的示例代码展示了如何使用zoo包中的rollmean函数计算居中移动平均和尾随移动平均。

library(tidyverse)
library(zoo)

some_data = tibble(day = 1:10)
# cma = centered moving average
# tma = trailing moving average
some_data = some_data %>%
    mutate(cma = rollmean(day, k = 3, fill = NA)) %>%
    mutate(tma = rollmean(day, k = 3, fill = NA, align = "right"))
some_data
#> # A tibble: 10 x 3
#>      day   cma   tma
#>    <int> <dbl> <dbl>
#>  1     1    NA    NA
#>  2     2     2    NA
#>  3     3     3     2
#>  4     4     4     3
#>  5     5     5     4
#>  6     6     6     5
#>  7     7     7     6
#>  8     8     8     7
#>  9     9     9     8
#> 10    10    NA     9

滑块包可以用于此。它有一个专门设计的界面，感觉类似呜呜声。它接受任何任意函数，并可以返回任何类型的输出。数据帧甚至按行迭代。pkgdown网站在这里。

library(slider)

x <- 1:3

# Mean of the current value + 1 value before it
# returned as a double vector
slide_dbl(x, ~mean(.x, na.rm = TRUE), .before = 1)
#> [1] 1.0 1.5 2.5


df <- data.frame(x = x, y = x)

# Slide row wise over data frames
slide(df, ~.x, .before = 1)
#> [[1]]
#>   x y
#> 1 1 1
#> 
#> [[2]]
#>   x y
#> 1 1 1
#> 2 2 2
#> 
#> [[3]]
#>   x y
#> 1 2 2
#> 2 3 3

滑块和数据的开销。Table的frollapply()应该非常低(比zoo快得多)。对于这个简单的示例，Frollapply()看起来稍微快一些，但请注意，它只接受数字输入，并且输出必须是标量数值。滑块函数是完全通用的，你可以返回任何数据类型。

library(slider)
library(zoo)
library(data.table)

x <- 1:50000 + 0L

bench::mark(
  slider = slide_int(x, function(x) 1L, .before = 5, .complete = TRUE),
  zoo = rollapplyr(x, FUN = function(x) 1L, width = 6, fill = NA),
  datatable = frollapply(x, n = 6, FUN = function(x) 1L),
  iterations = 200
)
#> # A tibble: 3 x 6
#>   expression      min   median `itr/sec` mem_alloc `gc/sec`
#>   <bch:expr> <bch:tm> <bch:tm>     <dbl> <bch:byt>    <dbl>
#> 1 slider      19.82ms   26.4ms     38.4    829.8KB     19.0
#> 2 zoo        177.92ms  211.1ms      4.71    17.9MB     24.8
#> 3 datatable    7.78ms   10.9ms     87.9    807.1KB     38.7

事实上，RcppRoll非常好。

cantdutchthis发布的代码必须在窗口的第四行进行修正:

ma <- function(arr, n=15){
  res = arr
  for(i in n:length(arr)){
    res[i] = mean(arr[(i-n+1):i])
  }
  res
}

这里给出了另一种处理缺失的方法。

第三种方法，改进cantdutch这段代码来计算部分平均与否，如下:

  ma <- function(x, n=2,parcial=TRUE){
  res = x #set the first values

  if (parcial==TRUE){
    for(i in 1:length(x)){
      t<-max(i-n+1,1)
      res[i] = mean(x[t:i])
    }
    res

  }else{
    for(i in 1:length(x)){
      t<-max(i-n+1,1)
      res[i] = mean(x[t:i])
    }
    res[-c(seq(1,n-1,1))] #remove the n-1 first,i.e., res[c(-3,-4,...)]
  }
}

使用费用应充分、有效。假设你有一个向量x，你想要n个数的和

cx <- c(0,cumsum(x))
rsum <- (cx[(n+1):length(cx)] - cx[1:(length(cx) - n)]) / n

正如@mzuther在评论中指出的那样，这假设数据中没有NAs。要处理这些问题，需要将每个窗口除以非na值的数量。这里有一种方法，结合@里卡多·克鲁兹的评论:

cx <- c(0, cumsum(ifelse(is.na(x), 0, x)))
cn <- c(0, cumsum(ifelse(is.na(x), 0, 1)))
rx <- cx[(n+1):length(cx)] - cx[1:(length(cx) - n)]
rn <- cn[(n+1):length(cx)] - cn[1:(length(cx) - n)]
rsum <- rx / rn

这仍然有一个问题，如果窗口中的所有值都是NAs，那么将会有一个零误差的除法。

下面是一个简单的带有过滤器的函数，演示了一种方法来处理带有填充的开始和结束NAs，并使用自定义权重计算加权平均值(由过滤器支持):

wma <- function(x) { 
  wts <- c(seq(0.5, 4, 0.5), seq(3.5, 0.5, -0.5))
  nside <- (length(wts)-1)/2
  # pad x with begin and end values for filter to avoid NAs
  xp <- c(rep(first(x), nside), x, rep(last(x), nside)) 
  z <- stats::filter(xp, wts/sum(wts), sides = 2) %>% as.vector 
  z[(nside+1):(nside+length(x))]
}

为了配合坎迪奇西斯和罗德里戈·雷麦黛奥的回答;

moving_fun <- function(x, w, FUN, ...) {
  # x: a double vector
  # w: the length of the window, i.e., the section of the vector selected to apply FUN
  # FUN: a function that takes a vector and return a summarize value, e.g., mean, sum, etc.
  # Given a double type vector apply a FUN over a moving window from left to the right, 
  #    when a window boundary is not a legal section, i.e. lower_bound and i (upper bound) 
  #    are not contained in the length of the vector, return a NA_real_
  if (w < 1) {
    stop("The length of the window 'w' must be greater than 0")
  }
  output <- x
  for (i in 1:length(x)) {
     # plus 1 because the index is inclusive with the upper_bound 'i'
    lower_bound <- i - w + 1
    if (lower_bound < 1) {
      output[i] <- NA_real_
    } else {
      output[i] <- FUN(x[lower_bound:i, ...])
    }
  }
  output
}

# example
v <- seq(1:10)

# compute a MA(2)
moving_fun(v, 2, mean)

# compute moving sum of two periods
moving_fun(v, 2, sum)