Create a tsibble object
tsibble(..., key = id(), index, regular = TRUE)A set of name-value pairs. The names of "key" and "index" should be avoided as they are used as the arguments.
Structural variable(s) that define unique time indices, used with
the helper id. If a univariate time series (without an explicit key),
simply call id(). See below for details.
A bare (or unquoted) variable to specify the time index variable.
Regular time interval (TRUE) or irregular (FALSE). The
interval is determined by the greatest common divisor of positive time distances,
if TRUE.
A tsibble object.
The time indices are preserved as the essential data component of the tsibble,
instead of implicit attribute (for example, the tsp attribute in a ts object). A
few index classes, such as Date, POSIXct, and difftime, forms the basis of
the tsibble, with new additions yearweek, yearmonth, and yearquarter
representing year-week, year-month, and year-quarter respectively. Any arbitrary
index class are also supported, including zoo::yearmth, zoo::yearqtr, and
nanotime.
For a tbl_ts of regular interval,
a choice of index representation has to be made. For example, a monthly data
should correspond to time index created by yearmonth or zoo::yearmth,
instead of Date or POSIXct. Because months in a year ensures the regularity,
12 months every year. However, if using Date, a month contains days ranging
from 28 to 31 days, which results in irregular time space. This is also applicable
to year-week and year-quarter.
Since the tibble that underlies the tsibble only accepts a 1d atomic
vector or a list, a tbl_ts doesn't accept POSIXlt and timeDate columns.
Key variable(s) together with the index uniquely identifies each record. And the key also imposes the structure on a tsibble, which can be created via the id function as identifiers:
None: an implicit variable id() resulting a univariate time series.
A single variable: an explicit variable. For example, data(pedestrian)
uses the id(Sensor) column as the key.
Nested variables: a nesting of one variable under another. For example,
data(tourism) contains two geographical locations: Region and State.
Region is the lower level than State in Australia; in other words, Region
is nested into State, which naturally forms a hierarchy. A vertical bar (|)
is used to describe this nesting relationship, and thus Region | State.
In theory, nesting can involve infinite levels, so is tsibble.
Crossed variables: a crossing of one variable with another. For example,
the geographical locations are crossed with the purpose of visiting (Purpose)
in the data(tourism). A comma (,) is used to indicate this crossing
relationship. Nested and crossed variables can be combined, such as
data(tourism) using id(Region | State, Purpose).
These key variables describe the data structure, which will prove useful in data visualisation and statistical modelling.
The interval function returns the interval associated with the tsibble.
Regular: the value and its time unit including "nanosecond", "microsecond", "millisecond", "second", "minute", "hour", "day", "week", "month", "quarter", "year". An unrecognisable time interval is labelled as "unit".
Irregular: as_tsibble(regular = FALSE) gives the irregular tsibble. It is
marked with !.
Unknown: if there is only one entry for each key variable, the interval
cannot be determined (?).
An interval is obtained based on the corresponding index representation:
integer/numeric: either "unit" or "year"
yearquarter/yearqtr: "quarter"
yearmonth/yearmth: "month"
yearweek: "week"
Date: "day"
POSIXct: "hour", "minute", "second", "millisecond", "microsecond"
nanotime: "nanosecond"
A tsibble is sorted by its key first and index.
# NOT RUN {
# create a tsibble w/o a key ----
tsbl1 <- tsibble(
date = seq(as.Date("2017-01-01"), as.Date("2017-01-10"), by = 1),
value = rnorm(10),
key = id(), index = date
)
tsbl1
# create a tsibble with one key ----
tsbl2 <- tsibble(
qtr = rep(yearquarter(seq(2010, 2012.25, by = 1 / 4)), 3),
group = rep(c("x", "y", "z"), each = 10),
value = rnorm(30),
key = id(group), index = qtr
)
tsbl2
# }
Run the code above in your browser using DataLab