```
rollapply(data, ...)
"rollapply"(data, ...)
"rollapply"(data, width, FUN, ..., by = 1, by.column = TRUE, fill = if (na.pad) NA, na.pad = FALSE, partial = FALSE, align = c("center", "left", "right"))
"rollapply"(data, ...)
rollapplyr(..., align = "right")
```

data

the data to be used (representing a series of observations).

width

numeric vector or list. In the simplest case this is an integer
specifying the window width (in numbers of observations) which is aligned
to the original sample according to the

`align`

argument. Alternatively,
`width`

can be a list regarded as offsets compared to the current
time, see below for details.FUN

the function to be applied.

...

optional arguments to

`FUN`

.by

calculate FUN at every

`by`

-th time point rather than
every point. `by`

is only used if `width`

is length 1 and either
a plain scalar or a list.by.column

logical. If

`TRUE`

, `FUN`

is applied to each column separately.fill

a three-component vector or list (recycled otherwise) providing
filling values at the left/within/to the right of the data range.
See the

`fill`

argument of `na.fill`

for details.na.pad

deprecated. Use

`fill = NA`

instead of `na.pad = TRUE`

.partial

logical or numeric. If

`FALSE`

(default) then `FUN`

is only
applied when all indexes of the rolling window are within the observed time range.
If `TRUE`

, then the subset of indexes that are in range are passed to `FUN`

.
A numeric argument to `partial`

can be used to determin the minimal
window size for partial computations. See below for more details.align

specifyies whether the index of the result
should be left- or right-aligned or centered (default) compared
to the rolling window of observations. This argument is only used if

`width`

represents widths.-
A object of the same class as

`data`

with the results of the rolling function.
`width`

is a plain numeric vector its elements are regarded as widths
to be interpreted in conjunction with `align`

whereas if `width`

is a list
its components are regarded as offsets. In the above cases if the length of
`width`

is 1 then `width`

is recycled for every `by`

-th point.
If `width`

is a list its components represent integer offsets such that
the i-th component of the list refers to time points at positions
`i + width[[i]]`

. If any of these points are below 1 or above the
length of `index(data)`

then `FUN`

is not evaluated for that
point unless `partial = TRUE`

and in that case only the valid
points are passed. The rolling function can also be applied to partial windows by setting `partial = TRUE`

For example, if `width = 3, align = "right"`

then for the first point
just that point is passed to `FUN`

since the two points to its
left are out of range. For the same example, if `partial = FALSE`

then `FUN`

is not
invoked at all for the first two points. If `partial`

is a numeric then it
specifies the minimum number of offsets that must be within range. Negative
`partial`

is interpreted as `FALSE`

.

If `FUN`

is `mean`

, `max`

or `median`

and `by.column`

is
`TRUE`

and width is a plain scalar and there are no other arguments
then special purpose code is used to enhance performance.
Also in the case of `mean`

such special purpose code is only invoked if the
`data`

argument has no `NA`

values.
See `rollmean`

, `rollmax`

and `rollmedian`

for more details.
Currently, there are methods for `"zoo"`

and `"ts"`

series
and `"default"`

method for ordinary vectors and matrices.

`rollapplyr`

is a wrapper around `rollapply`

that uses a default
of `align = "right"`

.

`rollmean`

## rolling mean z <- zoo(11:15, as.Date(31:35)) rollapply(z, 2, mean) ## non-overlapping means z2 <- zoo(rnorm(6)) rollapply(z2, 3, mean, by = 3) # means of nonoverlapping groups of 3 aggregate(z2, c(3,3,3,6,6,6), mean) # same ## optimized vs. customized versions rollapply(z2, 3, mean) # uses rollmean which is optimized for mean rollmean(z2, 3) # same rollapply(z2, 3, (mean)) # does not use rollmean ## rolling regression: ## set up multivariate zoo series with ## number of UK driver deaths and lags 1 and 12 seat <- as.zoo(log(UKDriverDeaths)) time(seat) <- as.yearmon(time(seat)) seat <- merge(y = seat, y1 = lag(seat, k = -1), y12 = lag(seat, k = -12), all = FALSE) ## run a rolling regression with a 3-year time window ## (similar to a SARIMA(1,0,0)(1,0,0)_12 fitted by OLS) rr <- rollapply(seat, width = 36, FUN = function(z) coef(lm(y ~ y1 + y12, data = as.data.frame(z))), by.column = FALSE, align = "right") ## plot the changes in coefficients ## showing the shifts after the oil crisis in Oct 1973 ## and after the seatbelt legislation change in Jan 1983 plot(rr) ## rolling mean by time window (e.g., 3 days) rather than ## by number of observations (e.g., when these are unequally spaced): # ## - test data tt <- as.Date("2000-01-01") + c(1, 2, 5, 6, 7, 8, 10) z <- zoo(seq_along(tt), tt) ## - fill it out to a daily series, zm, using NAs ## using a zero width zoo series g on a grid g <- zoo(, seq(start(z), end(z), "day")) zm <- merge(z, g) ## - 3-day rolling mean rollapply(zm, 3, mean, na.rm = TRUE, fill = NA) ## different values of rule argument z <- zoo(c(NA, NA, 2, 3, 4, 5, NA)) rollapply(z, 3, sum, na.rm = TRUE) rollapply(z, 3, sum, na.rm = TRUE, fill = NULL) rollapply(z, 3, sum, na.rm = TRUE, fill = NA) rollapply(z, 3, sum, na.rm = TRUE, partial = TRUE) # this will exclude time points 1 and 2 # It corresonds to align = "right", width = 3 rollapply(zoo(1:8), list(seq(-2, 0)), sum) # but this will include points 1 and 2 rollapply(zoo(1:8), list(seq(-2, 0)), sum, partial = 1) rollapply(zoo(1:8), list(seq(-2, 0)), sum, partial = 0) # so will this rollapply(zoo(1:8), list(seq(-2, 0)), sum, fill = NA) # by = 3, align = "right" L <- rep(list(NULL), 8) L[seq(3, 8, 3)] <- list(seq(-2, 0)) str(L) rollapply(zoo(1:8), L, sum) rollapply(zoo(1:8), list(0:2), sum, fill = 1:3) rollapply(zoo(1:8), list(0:2), sum, fill = 3) L2 <- rep(list(-(2:0)), 10) L2[5] <- list(NULL) str(L2) rollapply(zoo(1:10), L2, sum, fill = "extend") rollapply(zoo(1:10), L2, sum, fill = list("extend", NULL)) rollapply(zoo(1:10), L2, sum, fill = list("extend", NA)) rollapply(zoo(1:10), L2, sum, fill = NA) rollapply(zoo(1:10), L2, sum, fill = 1:3) rollapply(zoo(1:10), L2, sum, partial = TRUE) rollapply(zoo(1:10), L2, sum, partial = TRUE, fill = 99) rollapply(zoo(1:10), list(-1), sum, partial = 0) rollapply(zoo(1:10), list(-1), sum, partial = TRUE) rollapply(zoo(cbind(a = 1:6, b = 11:16)), 3, rowSums, by.column = FALSE) # these two are the same rollapply(zoo(cbind(a = 1:6, b = 11:16)), 3, sum) rollapply(zoo(cbind(a = 1:6, b = 11:16)), 3, colSums, by.column = FALSE) # these two are the same rollapply(zoo(1:6), 2, sum, by = 2, align = "right") aggregate(zoo(1:6), c(2, 2, 4, 4, 6, 6), sum) # these two are the same rollapply(zoo(1:3), list(-1), c) lag(zoo(1:3), -1) # these two are the same rollapply(zoo(1:3), list(1), c) lag(zoo(1:3)) # these two are the same rollapply(zoo(1:5), list(c(-1, 0, 1)), sum) rollapply(zoo(1:5), 3, sum) # these two are the same rollapply(zoo(1:5), list(0:2), sum) rollapply(zoo(1:5), 3, sum, align = "left") # these two are the same rollapply(zoo(1:5), list(-(2:0)), sum) rollapply(zoo(1:5), 3, sum, align = "right") # these two are the same rollapply(zoo(1:6), list(NULL, NULL, -(2:0)), sum) rollapply(zoo(1:6), 3, sum, by = 3, align = "right") # these two are the same rollapply(zoo(1:5), list(c(-1, 1)), sum) rollapply(zoo(1:5), 3, function(x) sum(x[-2])) # these two are the same rollapply(1:5, 3, rev) embed(1:5, 3) # these four are the same x <- 1:6 rollapply(c(0, 0, x), 3, sum, align = "right") - x rollapply(x, 3, sum, partial = TRUE, align = "right") - x rollapply(x, 3, function(x) sum(x[-3]), partial = TRUE, align = "right") rollapply(x, list(-(2:1)), sum, partial = 0) # same as Matlab's buffer(x, n, p) for valid non-negative p # See http://www.mathworks.com/help/toolbox/signal/buffer.html x <- 1:30; n <- 7; p <- 3 t(rollapply(c(rep(0, p), x, rep(0, n-p)), n, by = n-p, c)) # these three are the same y <- 10 * seq(8); k <- 4; d <- 2 # 1 # from http://ucfagls.wordpress.com/2011/06/14/embedding-a-time-series-with-time-delay-in-r-part-ii/ Embed <- function(x, m, d = 1, indices = FALSE, as.embed = TRUE) { n <- length(x) - (m-1)*d X <- seq_along(x) if(n <= 0) stop("Insufficient observations for the requested embedding") out <- matrix(rep(X[seq_len(n)], m), ncol = m) out[,-1] <- out[,-1, drop = FALSE] + rep(seq_len(m - 1) * d, each = nrow(out)) if(as.embed) out <- out[, rev(seq_len(ncol(out)))] if(!indices) out <- matrix(x[out], ncol = m) out } Embed(y, k, d) # 2 rollapply(y, list(-d * seq(0, k-1)), c) # 3 rollapply(y, d*k-1, function(x) x[d * seq(k-1, 0) + 1])

Run the code above in your browser using DataCamp Workspace