James Taylor James Taylor - 2 years ago 142
R Question

How to create leading lagged time series using - xts R package

I have monthly data over 2 years and 5 month. I want to have lead lagged values for next 7 months (future) starting from June 2017 till Dec 2017 ...

## DataSet

nr_serie_titles_live
2015-01-01 165
2015-02-01 170
2015-03-01 178
2015-04-01 188
2015-05-01 188
2015-06-01 194
2015-07-01 207
2015-08-01 216
2015-09-01 222
2015-10-01 226
2015-11-01 234
2015-12-01 237
2016-01-01 236
2016-02-01 245
2016-03-01 262
2016-04-01 266
2016-05-01 272
2016-06-01 275
2016-07-01 279
2016-08-01 281
2016-09-01 291
2016-10-01 304
2016-11-01 314
2016-12-01 324
2017-01-01 315
2017-02-01 324
2017-03-01 335
2017-04-01 352
2017-05-01 365


and I want values for coming 7 months

## values needed for 7 months
nr_serie_titles_live
01-06-2017 -
01-07-2017 -
01-08-2017 -
01-09-2017 -
01-10-2017 -
01-11-2017 -
01-12-2017 -


I tried "xts" package.

head(lag(date , 12), n = 7)


but I I don't understand. How I can get value for each month. So I should end up with 36 month of data with 29 month of original values and 7 months for future lagged values.

dput of data



dput(xts_in_out_p_month)
structure(c(165, 170, 178, 188, 188, 194, 207, 216, 222, 226,
234, 237, 236, 245, 262, 266, 272, 275, 279, 281, 291, 304, 314,
324, 315, 324, 335, 352, 365), .Dim = c(29L, 1L), .Dimnames = list(
NULL, "nr_serie_titles_live"), index = structure(c(1420070400,
1422748800, 1425168000, 1427846400, 1430438400, 1433116800, 1435708800,
1438387200, 1441065600, 1443657600, 1446336000, 1448928000, 1451606400,
1454284800, 1456790400, 1459468800, 1462060800, 1464739200, 1467331200,
1470009600, 1472688000, 1475280000, 1477958400, 1480550400, 1483228800,
1485907200, 1488326400, 1491004800, 1493596800), tzone = "UTC",
tclass = "Date"), class = c("xts", "zoo"), .indexCLASS = "Date",
tclass = "Date", .indexTZ = "UTC", tzone = "UTC")


Your help would be much appreciated.
Many thanks in advance !!!!

Answer Source

From your question I quite honestly did not get what is your desired output, but maybe you want something like this:

carrylastNForward <- function(x, n) {
  p <- periodicity(x) # get end date date and frequency
  xn <- length(x)     # length of current time series
  # create new time series time vector:
  newtimes <- seq(p$end, by = p$label, length.out = n + 1)[-1]
  new <- xts(x[(xn-n+1):length(x)], order.by = newtimes)
  c(x, new) # combine old and new time series
}

results:

> carrylastNForward(x, 7) # x <- xts_in_out_p_month
           nr_serie_titles_live
2015-01-01                  165
2015-02-01                  170
2015-03-01                  178
2015-04-01                  188
2015-05-01                  188
2015-06-01                  194
2015-07-01                  207
2015-08-01                  216
2015-09-01                  222
2015-10-01                  226
2015-11-01                  234
2015-12-01                  237
2016-01-01                  236
2016-02-01                  245
2016-03-01                  262
2016-04-01                  266
2016-05-01                  272
2016-06-01                  275
2016-07-01                  279
2016-08-01                  281
2016-09-01                  291
2016-10-01                  304
2016-11-01                  314
2016-12-01                  324
2017-01-01                  315
2017-02-01                  324
2017-03-01                  335
2017-04-01                  352
2017-05-01                  365
2017-06-01                  314
2017-07-01                  324
2017-08-01                  315
2017-09-01                  324
2017-10-01                  335
2017-11-01                  352
2017-12-01                  365
Recommended from our users: Dynamic Network Monitoring from WhatsUp Gold from IPSwitch. Free Download