3.6 The forecast package in R
This book uses the facilities in the
forecast package in R (which is loaded automatically whenever you load the
fpp2 package). This appendix briefly summarises some of the features of the package. Please refer to the help files for individual functions to learn more, and to see some examples of their use.
Functions that output a forecast object:
Many functions, including
rwf, produce output in the form of a
forecast object (i.e., an object of class
forecast). This allows other functions (such as
autoplot) to work consistently across a range of forecasting models.
Objects of class
forecast contain information about the forecasting method, the data used, the point forecasts obtained, prediction intervals, residuals and fitted values. There are several functions designed to work with these objects including
The following list shows all the functions that produce
So far we have used functions which produce a
forecast object directly. But a more common approach, which we will focus on in the rest of the book, will be to fit a model to the data, and then use the
forecast() function to produce forecasts from that model.
forecast() function works with many different types of input. It generally takes a time series or time series model as its main argument, and produces forecasts appropriately. It always returns objects of class
If the first argument is of class
ts, it returns forecasts from the automatic ETS algorithm discussed in Chapter 7.
Here is a simple example, applying
forecast() to the
forecast(ausbeer) #> Point Forecast Lo 80 Hi 80 Lo 95 Hi 95 #> 2010 Q3 405 386 423 376 433 #> 2010 Q4 480 458 503 446 515 #> 2011 Q1 417 397 437 386 448 #> 2011 Q2 383 364 402 354 413 #> 2011 Q3 403 381 425 369 437 #> 2011 Q4 478 451 506 436 521 #> 2012 Q1 415 390 441 377 454 #> 2012 Q2 382 357 406 344 419
That works quite well if you have no idea what sort of model to use. But by the end of this book, you should not need to use
forecast() in this “blind” fashion. Instead, you will fit a model appropriate to the data, and then use
forecast() to produce forecasts from that model.