Exercise 2.1

Explore the following four time series: Bricks from aus_production, Lynx from pelt, Close from gafa_stock, Demand from vic_elec.- Use ? (or help()) to find out about the data in each series.- What is the time interval of each series?- Use autoplot() to produce a time plot of each series.- For the last plot, modify the axis labels and title.

library(fpp3)
## Registered S3 method overwritten by 'tsibble':
##   method               from 
##   as_tibble.grouped_df dplyr
## ── Attaching packages ──────────────────────────────────────────── fpp3 1.0.1 ──
## âś” tibble      3.2.1     âś” tsibble     1.1.6
## âś” dplyr       1.1.4     âś” tsibbledata 0.4.1
## âś” tidyr       1.3.1     âś” feasts      0.4.1
## âś” lubridate   1.9.4     âś” fable       0.4.1
## âś” ggplot2     3.5.1
## ── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
## âś– lubridate::date()    masks base::date()
## âś– dplyr::filter()      masks stats::filter()
## âś– tsibble::intersect() masks base::intersect()
## âś– tsibble::interval()  masks lubridate::interval()
## âś– dplyr::lag()         masks stats::lag()
## âś– tsibble::setdiff()   masks base::setdiff()
## âś– tsibble::union()     masks base::union()
library(tsibble)

?aus_production
## starting httpd help server ...
##  done
?pelt
?gafa_stock
?vic_elec

Now we look at the intervals

interval(aus_production)
## <interval[1]>
## [1] 1Q
interval(pelt)
## <interval[1]>
## [1] 1Y
interval(gafa_stock)
## <interval[1]>
## [1] !
interval(vic_elec)
## <interval[1]>
## [1] 30m

Exercist 2.2

Use filter() to find what days corresponded to the peak closing price for each of the four stocks in gafa_stock.

gafa_max_close <- gafa_stock |>
  group_by(Symbol) |>
  filter(Close == max(Close)) |>
  select(Symbol, Date)

print(gafa_max_close)
## # A tsibble: 4 x 2 [!]
## # Key:       Symbol [4]
## # Groups:    Symbol [4]
##   Symbol Date      
##   <chr>  <date>    
## 1 AAPL   2018-10-03
## 2 AMZN   2018-09-04
## 3 FB     2018-07-25
## 4 GOOG   2018-07-26

Exercise 2.3

Download the file tute1.csv from the book website, open it in Excel (or some other spreadsheet application), and review its contents. You should find four columns of information. Columns B through D each contain a quarterly series, labelled Sales, AdBudget and GDP. Sales contains the quarterly sales for a small company over the period 1981-2005. AdBudget is the advertising budget and GDP is the gross domestic product. All series have been adjusted for inflation. a. You can read the data into R with the following script:

tute1 <- readr::read_csv("tute1.csv")
## Rows: 100 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl  (3): Sales, AdBudget, GDP
## date (1): Quarter
## 
## â„ą Use `spec()` to retrieve the full column specification for this data.
## â„ą Specify the column types or set `show_col_types = FALSE` to quiet this message.
View(tute1)
  1. Convert the data to time series
mytimeseries <- tute1 |>
  mutate(Quarter = yearquarter(Quarter)) |>
  as_tsibble(index = Quarter)
view(mytimeseries)
  1. Construct time series plots of each of the three series
mytimeseries |>
  pivot_longer(-Quarter) |>
  ggplot(aes(x = Quarter, y = value, colour = name)) +
  geom_line() +
  facet_grid(name ~ ., scales = "free_y")

Without facet_grid(), does not separate the three names, might be harder to see in other cases.

mytimeseries |>
  pivot_longer(-Quarter) |>
  ggplot(aes(x = Quarter, y = value, colour = name)) +
  geom_line()

Execise 2.4

  1. Install the USgas package.
  2. Create a tsibble from us_total with year as the index and state as the key.
  3. Plot the annual natural gas consumption by state for the New England area (comprising the states of Maine, Vermont, New Hampshire, Massachusetts, Connecticut and Rhode Island).
library(USgas)

us_total <- us_total |>
  as_tsibble(index = year, key = state)

us_total |>
  filter(state %in% c("Maine", "Vermont", "New Hampshire", "Massachusetts", "Connecticut", "Rhode Island")) |>
  ggplot(aes(x = year, y = y)) +
  geom_line() +
  facet_grid(state ~ ., scales = "free_y") +
  labs(title = "Annual Natural Gas Consumption by States",
       y = "Gas Consumption")

Execise 2.5

  1. Download tourism.xlsx from the book website and read it into R using readxl::read_excel().
  2. Create a tsibble which is identical to the tourism tsibble from the tsibble package.
library(readxl)
tourism <- read_excel("tourism.xlsx")
view(tourism)

tourism_tsibble <- tourism |>
  mutate(Quarter = yearquarter(Quarter)) |>
  as_tsibble(key = c(Region, State, Purpose), index = Quarter)
  1. Find what combination of Region and Purpose had the maximum number of overnight trips on average.
max_trips <- tourism |>
  group_by(Region, Purpose) |>
  summarise(avg_trips = mean(Trips),  .groups = 'drop') |>
  filter(avg_trips == max(avg_trips)) |>
  select(Region, Purpose)

print(max_trips)
## # A tibble: 1 Ă— 2
##   Region Purpose 
##   <chr>  <chr>   
## 1 Sydney Visiting
  1. Create a new tsibble which combines the Purposes and Regions, and just has total trips by State.
new_tib <- tourism |>
  group_by(State) |>
  summarise(total_trips = sum(Trips))

print(new_tib)
## # A tibble: 8 Ă— 2
##   State              total_trips
##   <chr>                    <dbl>
## 1 ACT                     41007.
## 2 New South Wales        557367.
## 3 Northern Territory      28614.
## 4 Queensland             386643.
## 5 South Australia        118151.
## 6 Tasmania                54137.
## 7 Victoria               390463.
## 8 Western Australia      147820.

Exercise 2.8

Use the following graphics functions: autoplot(), gg_season(), gg_subseries(), gg_lag(), ACF() and explore features from the following time series: “Total Private” Employed from us_employment, Bricks from aus_production, Hare from pelt, “H02” Cost from PBS, and Barrels from us_gasoline.

us_employment |>
  filter(Title == "Total Private") |>
  autoplot(Employed)

us_employment |> filter(Title == "Total Private") |>
  gg_season(Employed)

us_employment |> filter(Title == "Total Private") |>
  gg_subseries(Employed)

us_employment |> filter(Title == "Total Private") |>
  gg_lag(Employed)

us_employment |> filter(Title == "Total Private") |>
  ACF(Employed) |>
  autoplot()

aus_production |> autoplot(Bricks)
## Warning: Removed 20 rows containing missing values or values outside the scale range
## (`geom_line()`).

aus_production |> gg_season(Bricks)
## Warning: Removed 20 rows containing missing values or values outside the scale range
## (`geom_line()`).

aus_production |> gg_subseries(Bricks)
## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_line()`).

aus_production |> gg_lag(Bricks)
## Warning: Removed 20 rows containing missing values (gg_lag).

aus_production |> ACF(Bricks) |>
  autoplot()

pelt |> autoplot(Hare)

pelt |> gg_subseries(Hare)

pelt |> gg_lag(Hare)

pelt |> ACF(Hare) |>
  autoplot()

PBS |> filter(ATC2 == "H02") |>
  autoplot(Cost)

PBS |>  filter(ATC2 == "H02") |>
  gg_season(Cost)

PBS |>  filter(ATC2 == "H02") |>
  gg_subseries(Cost)

# Does not work 
#PBS |>  filter(ATC2 == "H02") |>
#  gg_lag(Cost)

PBS |>  filter(ATC2 == "H02") |>
  ACF(Cost)
us_gasoline |> autoplot(Barrels)

us_gasoline |> gg_season(Barrels)

us_gasoline |> gg_subseries(Barrels)

us_gasoline |> gg_lag(Barrels)

us_gasoline |> ACF(Barrels) |>
  autoplot()