vector_avg <- function(x){
  sum_x = 0
  for(i in 1:length(x)){
    if(!is.na(x[i]))
      sum_x = sum_x + x[i]
  }
  return(sum_x/length(x))
}

在数据。表1.12.0增加了新的滚动平均值函数，以计算快速和准确的滚动平均值，仔细处理NA, NaN和+Inf， -Inf值。

由于在这个问题中没有可重复的例子，所以在这里没有更多的问题要解决。

你可以在手册中找到更多关于?frollmean的信息，也可以在?frollmean网站上找到。

下面是手册中的例子:

library(data.table)
d = as.data.table(list(1:6/2, 3:8/4))

# rollmean of single vector and single window
frollmean(d[, V1], 3)

# multiple columns at once
frollmean(d, 3)

# multiple windows at once
frollmean(d[, .(V1)], c(3, 4))

# multiple columns and multiple windows at once
frollmean(d, c(3, 4))

## three above are embarrassingly parallel using openmp

你可以通过以下方法计算窗口宽度为k的向量x的移动平均值:

apply(embed(x, k), 1, mean)

编辑:非常喜欢添加侧参数，例如，一个日期向量的过去7天的移动平均值(或总和，或…)。

对于那些只想自己计算的人来说，它无非是:

# x = vector with numeric data
# w = window length
y <- numeric(length = length(x))

for (i in seq_len(length(x))) {
  ind <- c((i - floor(w / 2)):(i + floor(w / 2)))
  ind <- ind[ind %in% seq_len(length(x))]
  y[i] <- mean(x[ind])
}

y

但是让它独立于mean()会很有趣，所以你可以计算任何“移动”函数!

# our working horse:
moving_fn <- function(x, w, fun, ...) {
  # x = vector with numeric data
  # w = window length
  # fun = function to apply
  # side = side to take, (c)entre, (l)eft or (r)ight
  # ... = parameters passed on to 'fun'
  y <- numeric(length(x))
  for (i in seq_len(length(x))) {
    if (side %in% c("c", "centre", "center")) {
      ind <- c((i - floor(w / 2)):(i + floor(w / 2)))
    } else if (side %in% c("l", "left")) {
      ind <- c((i - floor(w) + 1):i)
    } else if (side %in% c("r", "right")) {
      ind <- c(i:(i + floor(w) - 1))
    } else {
      stop("'side' must be one of 'centre', 'left', 'right'", call. = FALSE)
    }
    ind <- ind[ind %in% seq_len(length(x))]
    y[i] <- fun(x[ind], ...)
  }
  y
}

# and now any variation you can think of!
moving_average <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = mean, side = side, na.rm = na.rm)
}

moving_sum <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = sum, side = side, na.rm = na.rm)
}

moving_maximum <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = max, side = side, na.rm = na.rm)
}

moving_median <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = median, side = side, na.rm = na.rm)
}

moving_Q1 <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = quantile, side = side, na.rm = na.rm, 0.25)
}

moving_Q3 <- function(x, w = 5, side = "centre", na.rm = FALSE) {
  moving_fn(x = x, w = w, fun = quantile, side = side, na.rm = na.rm, 0.75)
}

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

我使用聚合和一个由rep()创建的向量。这样做的好处是可以使用cbind()一次在数据帧中聚合1个以上的列。下面是一个长度为1000的向量(v)的移动平均值为60的例子:

v=1:1000*0.002+rnorm(1000)
mrng=rep(1:round(length(v)/60+0.5), length.out=length(v), each=60)
aggregate(v~mrng, FUN=mean, na.rm=T)

请注意，rep中的第一个参数只是根据向量的长度和要平均的数量，为移动范围获取足够的唯一值;第二个参数保持长度等于向量长度，最后一个参数重复第一个参数的值的次数与平均周期相同。

总的来说，你可以使用几个函数(中值，最大值，最小值)-例如所示的平均值。同样，could可以使用cbind公式对数据帧中的多个(或所有)列执行此操作。