R: Examples for 'zoo::aggregate.zoo'

### ** Examples

## averaging over values in a month:
# x.date is jan 1,3,5,7; feb 9,11,13; mar 15,17,19
x.date <- as.Date(paste(2004, rep(1:4, 4:1), seq(1,20,2), sep = "-")); x.date

 [1] "2004-01-01" "2004-01-03" "2004-01-05" "2004-01-07" "2004-02-09"
 [6] "2004-02-11" "2004-02-13" "2004-03-15" "2004-03-17" "2004-04-19"

x <- zoo(rnorm(12), x.date); x

 2004-01-01  2004-01-03  2004-01-05  2004-01-07  2004-02-09  2004-02-11 
 0.26758992 -0.20333383 -0.07921181  0.78892774 -1.59444641 -1.55243485 
 2004-02-13  2004-03-15  2004-03-17  2004-04-19 
 0.41343957 -0.74059832 -0.76113172 -1.43842639

# coarser dates - jan 1 (4 times), feb 1 (3 times), mar 1 (3 times)
x.date2 <- as.Date(paste(2004, rep(1:4, 4:1), 1, sep = "-")); x.date2

 [1] "2004-01-01" "2004-01-01" "2004-01-01" "2004-01-01" "2004-02-01"
 [6] "2004-02-01" "2004-02-01" "2004-03-01" "2004-03-01" "2004-04-01"

x2 <- aggregate(x, x.date2, mean); x2

2004-01-01 2004-02-01 2004-03-01 2004-04-01 
 0.1934930 -0.9111472 -0.7508650 -1.4384264

# same - uses as.yearmon
x2a <- aggregate(x, as.Date(as.yearmon(time(x))), mean); x2a

2004-01-01 2004-02-01 2004-03-01 2004-04-01 
 0.1934930 -0.9111472 -0.7508650 -1.4384264

# same - uses by function
x2b <- aggregate(x, function(tt) as.Date(as.yearmon(tt)), mean); x2b

2004-01-01 2004-02-01 2004-03-01 2004-04-01 
 0.1934930 -0.9111472 -0.7508650 -1.4384264

# same - uses cut
x2c <- aggregate(x, as.Date(cut(time(x), "month")), mean); x2c

2004-01-01 2004-02-01 2004-03-01 2004-04-01 
 0.1934930 -0.9111472 -0.7508650 -1.4384264

# almost same but times of x2d have yearmon class rather than Date class
x2d <- aggregate(x, as.yearmon, mean); x2d

  Jan 2004   Feb 2004   Mar 2004   Apr 2004 
 0.1934930 -0.9111472 -0.7508650 -1.4384264

# compare time series
plot(x)
lines(x2, col = 2)

plot of chunk example-zoo-aggregate.zoo-1

## aggregate a daily time series to a quarterly series
# create zoo series
tt <- as.Date("2000-1-1") + 0:300
z.day <- zoo(0:300, tt)

# function which returns corresponding first "Date" of quarter
first.of.quarter <- function(tt) as.Date(as.yearqtr(tt))

# average z over quarters
# 1. via "yearqtr" index (regular)
# 2. via "Date" index (not regular)
z.qtr1 <- aggregate(z.day, as.yearqtr, mean)
z.qtr2 <- aggregate(z.day, first.of.quarter, mean)

# The last one used the first day of the quarter but suppose
# we want the first day of the quarter that exists in the series
# (and the series does not necessarily start on the first day
# of the quarter).
z.day[!duplicated(as.yearqtr(time(z.day)))]

2000-01-01 2000-04-01 2000-07-01 2000-10-01 
         0         91        182        274

# This is the same except it uses the last day of the quarter.
# It requires R 2.6.0 which introduced the fromLast= argument.
## Not run: 
##D z.day[!duplicated(as.yearqtr(time(z.day)), fromLast = TRUE)]
## End(Not run)

# The aggregated series above are of class "zoo" (because z.day
# was "zoo"). To create a regular series of class "zooreg",
# the frequency can be automatically chosen
zr.qtr1 <- aggregate(z.day, as.yearqtr, mean, regular = TRUE)
# or specified explicitely
zr.qtr2 <- aggregate(z.day, as.yearqtr, mean, frequency = 4)


## aggregate on month and extend to monthly time series
if(require(chron)) {
y <- zoo(matrix(11:15, nrow = 5, ncol = 2), chron(c(15, 20, 80, 100, 110)))
colnames(y) <- c("A", "B")

# aggregate by month using first of month as times for coarser series
# using first day of month as repesentative time
y2 <- aggregate(y, as.Date(as.yearmon(time(y))), head, 1)

# fill in missing months by merging with an empty series containing
# a complete set of 1st of the months
yrt2 <- range(time(y2))
y0 <- zoo(,seq(from = yrt2[1], to = yrt2[2], by = "month"))
merge(y2, y0)
}

Loading required package: chron

            A  B
1970-01-01 11 11
1970-02-01 NA NA
1970-03-01 13 13
1970-04-01 14 14

# given daily series keep only first point in each month at
# day 21 or more
z <- zoo(101:200, as.Date("2000-01-01") + seq(0, length = 100, by = 2))
zz <- z[as.numeric(format(time(z), "%d")) >= 21]
zz[!duplicated(as.yearmon(time(zz)))]

2000-01-21 2000-02-22 2000-03-21 2000-04-22 2000-05-22 2000-06-21 
       111        127        141        157        172        187

# same except times are of "yearmon" class
aggregate(zz, as.yearmon, head, 1)

Jan 2000 Feb 2000 Mar 2000 Apr 2000 May 2000 Jun 2000 
     111      127      141      157      172      187

# aggregate POSIXct seconds data every 10 minutes
Sys.setenv(TZ = "GMT")
tt <- seq(10, 2000, 10)
x <- zoo(tt, structure(tt, class = c("POSIXt", "POSIXct")))
aggregate(x, time(x) - as.numeric(time(x)) %% 600, mean)

1970-01-01 00:00:00 1970-01-01 00:10:00 1970-01-01 00:20:00 1970-01-01 00:30:00 
                300                 895                1495                1900

# aggregate weekly series to a series with frequency of 52 per year
suppressWarnings(RNGversion("3.5.0"))
set.seed(1)
z <- zooreg(1:100 + rnorm(100), start = as.Date("2001-01-01"), deltat = 7)

# new.freq() converts dates to a grid of freq points per year
# yd is sequence of dates of firsts of years
# yy is years of the same sequence
# last line interpolates so dates, d, are transformed to year + frac of year
# so first week of 2001 is 2001.0, second week is 2001 + 1/52, third week
# is 2001 + 2/52, etc.
new.freq <- function(d, freq = 52) {
       y <- as.Date(cut(range(d), "years")) + c(0, 367)
       yd <- seq(y[1], y[2], "year")
       yy <- as.numeric(format(yd, "%Y"))
       floor(freq * approx(yd, yy, xout = d)$y) / freq
}

# take last point in each period
aggregate(z, new.freq, tail, 1)

  2001(1)   2001(2)   2001(3)   2001(4)   2001(5)   2001(6)   2001(7)   2001(8) 
 2.183643  2.164371  5.595281  5.329508  5.179532  7.487429  8.738325  9.575781 
  2001(9)  2001(10)  2001(11)  2001(12)  2001(13)  2001(14)  2001(15)  2001(16) 
 9.694612 12.511781 12.389843 12.378759 11.785300 16.124931 15.955066 16.983810 
 2001(17)  2001(18)  2001(19)  2001(20)  2001(21)  2001(22)  2001(23)  2001(24) 
18.943836 19.821221 20.593901 21.918977 22.782136 23.074565 22.010648 25.619826 
 2001(25)  2001(26)  2001(27)  2001(28)  2001(29)  2001(30)  2001(31)  2001(32) 
25.943871 26.844204 26.529248 28.521850 30.417942 32.358680 31.897212 33.387672 
 2001(33)  2001(34)  2001(35)  2001(36)  2001(37)  2001(38)  2001(39)  2001(40) 
33.946195 33.622940 35.585005 36.605710 37.940687 40.100025 40.763176 40.835476 
 2001(41)  2001(42)  2001(43)  2001(44)  2001(45)  2001(46)  2001(47)  2001(48) 
41.746638 43.696963 44.556663 44.311244 45.292505 47.364582 48.768533 48.887654 
 2001(49)  2001(50)  2001(51)  2001(52)   2002(1)   2002(2)   2002(3)   2002(4) 
50.881108 51.398106 51.387974 53.341120 52.870637 56.433024 57.980400 56.632779 
  2002(5)   2002(6)   2002(7)   2002(8)   2002(9)  2002(10)  2002(11)  2002(12) 
56.955865 59.569720 59.864945 63.401618 61.960760 63.689739 64.028002 64.256727 
 2002(13)  2002(14)  2002(15)  2002(16)  2002(17)  2002(18)  2002(19)  2002(20) 
66.188792 65.195041 69.465555 69.153253 72.172612 71.475510 71.290054 73.610726 
 2002(21)  2002(22)  2002(23)  2002(24)  2002(25)  2002(26)  2002(27)  2002(28) 
73.065902 73.746367 76.291446 76.556708 78.001105 79.074341 79.410479 80.431331 
 2002(29)  2002(30)  2002(31)  2002(32)  2002(33)  2002(34)  2002(35)  2002(36) 
81.864821 84.178087 82.476433 85.593946 86.332950 88.063100 87.695816 89.370019 
 2002(37)  2002(38)  2002(39)  2002(40)  2002(41)  2002(42)  2002(43)  2002(44) 
90.267099 90.457480 93.207868 94.160403 94.700214 96.586833 96.558486 95.723408 
 2002(45)  2002(46)  2002(47) 
97.426735 97.775387 99.526599

# or, take mean of all points in each
aggregate(z, new.freq, mean)

  2001(1)   2001(2)   2001(3)   2001(4)   2001(5)   2001(6)   2001(7)   2001(8) 
 1.278595  2.164371  5.595281  5.329508  5.179532  7.487429  8.738325  9.575781 
  2001(9)  2001(10)  2001(11)  2001(12)  2001(13)  2001(14)  2001(15)  2001(16) 
 9.694612 12.511781 12.389843 12.378759 11.785300 16.124931 15.955066 16.983810 
 2001(17)  2001(18)  2001(19)  2001(20)  2001(21)  2001(22)  2001(23)  2001(24) 
18.943836 19.821221 20.593901 21.918977 22.782136 23.074565 22.010648 25.619826 
 2001(25)  2001(26)  2001(27)  2001(28)  2001(29)  2001(30)  2001(31)  2001(32) 
25.943871 26.844204 26.529248 28.521850 30.417942 32.358680 31.897212 33.387672 
 2001(33)  2001(34)  2001(35)  2001(36)  2001(37)  2001(38)  2001(39)  2001(40) 
33.946195 33.622940 35.585005 36.605710 37.940687 40.100025 40.763176 40.835476 
 2001(41)  2001(42)  2001(43)  2001(44)  2001(45)  2001(46)  2001(47)  2001(48) 
41.746638 43.696963 44.556663 44.311244 45.292505 47.364582 48.768533 48.887654 
 2001(49)  2001(50)  2001(51)  2001(52)   2002(1)   2002(2)   2002(3)   2002(4) 
50.881108 51.398106 51.387974 53.341120 52.870637 56.433024 57.980400 56.632779 
  2002(5)   2002(6)   2002(7)   2002(8)   2002(9)  2002(10)  2002(11)  2002(12) 
56.955865 59.569720 59.864945 63.401618 61.960760 63.689739 64.028002 64.256727 
 2002(13)  2002(14)  2002(15)  2002(16)  2002(17)  2002(18)  2002(19)  2002(20) 
66.188792 65.195041 69.465555 69.153253 72.172612 71.475510 71.290054 73.610726 
 2002(21)  2002(22)  2002(23)  2002(24)  2002(25)  2002(26)  2002(27)  2002(28) 
73.065902 73.746367 76.291446 76.556708 78.001105 79.074341 79.410479 80.431331 
 2002(29)  2002(30)  2002(31)  2002(32)  2002(33)  2002(34)  2002(35)  2002(36) 
81.864821 84.178087 82.476433 85.593946 86.332950 88.063100 87.695816 89.370019 
 2002(37)  2002(38)  2002(39)  2002(40)  2002(41)  2002(42)  2002(43)  2002(44) 
90.267099 90.457480 93.207868 94.160403 94.700214 96.586833 96.558486 95.723408 
 2002(45)  2002(46)  2002(47) 
97.426735 97.775387 99.526599

# example of taking means in the presence of NAs
z.na <- zooreg(c(1:364, NA), start = as.Date("2001-01-01"))
aggregate(z.na, as.yearqtr, mean, na.rm = TRUE)

2001 Q1 2001 Q2 2001 Q3 2001 Q4 
   45.5   136.0   227.5   319.0

# Find the sd of all days that lie in any Jan, all days that lie in
# any Feb, ..., all days that lie in any Dec (i.e. output is vector with
# 12 components)
aggregate(z, format(time(z), "%m"), sd)

       01        02        03        04        05        06        07        08 
27.931987 27.985392 27.679111 27.774779 27.328400 27.840695 27.520893 28.058606 
       09        10        11        12 
27.806512 28.066187 27.406884  1.589453

Examples for 'zoo::aggregate.zoo'

Compute Summary Statistics of zoo Objects