Book Image

R for Data Science

By : Dan Toomey
Book Image

R for Data Science

By: Dan Toomey

Overview of this book

Table of Contents (19 chapters)

Automatic forecasting packages

In R, there are several packages that provide plotting for the programmer. We will be using the following packages in the examples:

  • forecast: This package is used to forecast functions for time series and linear models

  • TTR: This package has functions and data to create technical trading rules

Time series

In R programming, a time series is a sequence of data points measured evenly over uniform time intervals—typically, monthly or yearly frequencies are used. You can coerce (convert) a standard dataset into a time series using the as.ts function.

For the initial time series, we will use the Fraser River monthly flows (available at I couldn't find a source for the dataset, so I copied it from the site to a local file. The data is the monthly flow starting from March 1913. There are over 900 measurements. The data has a definite frequency:

> fraser <- scan("fraser.txt")
Read 946 items

If we look at the data with a standard plot, we don't see...