Explore the following four time series:
Bricksfromaus_production,Lynxfrompelt,Closefromgafa_stock,Demandfromvic_elec.
- Use
?(orhelp()) to find out about the data in each series.- What is the time interval of each series? c Use
autoplot()to produce a time plot of each series. d For the last plot, modify the axis labels and title.
# (a) data in each series
?aus_production
?pelt
?gafa_stock
?vic_elec
# (b) time interval
interval(aus_production) # 1Q = quarterly
## <interval[1]>
## [1] 1Q
interval(pelt) # 1Y = annual
## <interval[1]>
## [1] 1Y
interval(gafa_stock) # ! = irregular (trading days only, no fixed gap)
## <interval[1]>
## [1] !
interval(vic_elec) # 30m = half-hourly
## <interval[1]>
## [1] 30m
# (c) time plots
aus_production |> autoplot(Bricks, colour = 'hotpink')
pelt |> autoplot(Lynx, colour = "firebrick")
gafa_stock |> autoplot(Close, colour = "limegreen")
vic_elec |> autoplot(Demand, colour = "magenta")
# (d) relabeled plot
vic_elec |> autoplot(Demand, colour = "gold") +
labs(
title ="Recorded electricity demand (every 30 minutes):Victoria, Australia",
x = "Time",
y = "Demand (MWh)"
) +
theme(
plot.title = element_text(hjust = 0.5, colour = "gold", face = "bold"),
axis.title = element_text(colour = "gold", face = "bold"),
panel.background = element_rect(fill = "navyblue"),
plot.background = element_rect(fill = "navyblue"),
panel.grid = element_line(colour = "white"),
axis.text = element_text(colour = "gold", face = "bold")
)
Use filter() to find what days corresponded to the peak closing price for each of the four stocks in gafa_stock.
gafa_stock |>
group_by(Symbol) |>
filter(Close == max(Close)) |>
ungroup() |>
select(Symbol, Date, Close)
## # A tsibble: 4 x 3 [!]
## # Key: Symbol [4]
## Symbol Date Close
## <chr> <date> <dbl>
## 1 AAPL 2018-10-03 232.
## 2 AMZN 2018-09-04 2040.
## 3 FB 2018-07-25 218.
## 4 GOOG 2018-07-26 1268.
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) Read the data into R form the csv
tute1 <- readr::read_csv("tute1.csv")
## Rows: 100 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (3): Sales, AdBudget, GDP
## date (1): Quarter
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
glimpse(tute1)
## Rows: 100
## Columns: 4
## $ Quarter <date> 1981-03-01, 1981-06-01, 1981-09-01, 1981-12-01, 1982-03-01, …
## $ Sales <dbl> 1020.2, 889.2, 795.0, 1003.9, 1057.7, 944.4, 778.5, 932.5, 99…
## $ AdBudget <dbl> 659.2, 589.0, 512.5, 614.1, 647.2, 602.0, 530.7, 608.4, 637.9…
## $ GDP <dbl> 251.8, 290.9, 290.8, 292.4, 279.1, 254.0, 295.6, 271.7, 259.6…
# (b) convert to tsibble
mytimeseries <- tute1 |>
mutate(Quarter = yearquarter(Quarter)) |>
as_tsibble(index = Quarter)
mytimeseries
## # A tsibble: 100 x 4 [1Q]
## Quarter Sales AdBudget GDP
## <qtr> <dbl> <dbl> <dbl>
## 1 1981 Q1 1020. 659. 252.
## 2 1981 Q2 889. 589 291.
## 3 1981 Q3 795 512. 291.
## 4 1981 Q4 1004. 614. 292.
## 5 1982 Q1 1058. 647. 279.
## 6 1982 Q2 944. 602 254
## 7 1982 Q3 778. 531. 296.
## 8 1982 Q4 932. 608. 272.
## 9 1983 Q1 996. 638. 260.
## 10 1983 Q2 908. 582. 280.
## # ℹ 90 more rows
# (c) time series plots, faceted
mytimeseries |>
pivot_longer(-Quarter) |>
ggplot(aes(x = Quarter, y = value, colour = name)) +
geom_line() +
facet_grid(name ~ ., scales = "free_y")
# Checking what happens when you don’t include facet_grid().
# Without facet_grid(), all three series share a single y-axis, which compresses GDP's variation (since its values are much smaller than Sales and AdBudget) and makes it harder to see its trend clearly. facet_grid(name ~ ., scales = "free_y") gives each series its own scale, making all three trends individually readable.
mytimeseries |>
pivot_longer(-Quarter) |>
ggplot(aes(x = Quarter, y = value, colour = name)) +
geom_line()
The USgas package contains data on the demand for natural gas in the US.
# (a)Install the USgas packag
library(USgas)
#(b)Create a tsibble from us_total with year as the index and state as the key.
us_total_ts <- us_total |>
as_tsibble(index = year, key = state)
us_total_ts
## # A tsibble: 1,266 x 3 [1Y]
## # Key: state [53]
## year state y
## <int> <chr> <int>
## 1 1997 Alabama 324158
## 2 1998 Alabama 329134
## 3 1999 Alabama 337270
## 4 2000 Alabama 353614
## 5 2001 Alabama 332693
## 6 2002 Alabama 379343
## 7 2003 Alabama 350345
## 8 2004 Alabama 382367
## 9 2005 Alabama 353156
## 10 2006 Alabama 391093
## # ℹ 1,256 more rows
# (c)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).
us_total_ts |>
filter(state %in% c("Maine", "Vermont", "New Hampshire",
"Massachusetts", "Connecticut", "Rhode Island")) |>
autoplot(y) +
scale_y_continuous(labels = scales::comma) +
labs(
title = "Annual Natural Gas Consumption: New England States",
x = "Year",
y = "Consumption"
)
- Download tourism.xlsx from the book website and read it into R using readxl::read_excel().
- Create a tsibble which is identical to the tourism tsibble from the tsibble package.
- Find what combination of Region and Purpose had the maximum number of overnight trips on average.
- Create a new tsibble which combines the Purposes and Regions, and just > has total trips by State.
#(a)
tourism_raw <- readxl::read_excel("tourism.xlsx")
#(b)
tourism_ts <- tourism_raw |>
mutate(Quarter = yearquarter(Quarter)) |>
as_tsibble(index = Quarter, key = c(Region, State, Purpose))
tourism_ts
## # A tsibble: 24,320 x 5 [1Q]
## # Key: Region, State, Purpose [304]
## Quarter Region State Purpose Trips
## <qtr> <chr> <chr> <chr> <dbl>
## 1 1998 Q1 Adelaide South Australia Business 135.
## 2 1998 Q2 Adelaide South Australia Business 110.
## 3 1998 Q3 Adelaide South Australia Business 166.
## 4 1998 Q4 Adelaide South Australia Business 127.
## 5 1999 Q1 Adelaide South Australia Business 137.
## 6 1999 Q2 Adelaide South Australia Business 200.
## 7 1999 Q3 Adelaide South Australia Business 169.
## 8 1999 Q4 Adelaide South Australia Business 134.
## 9 2000 Q1 Adelaide South Australia Business 154.
## 10 2000 Q2 Adelaide South Australia Business 169.
## # ℹ 24,310 more rows
#(c)
tourism_ts |>
as_tibble() |>
group_by(Region, Purpose) |>
summarise(Trips = mean(Trips), .groups = "drop") |>
filter(Trips == max(Trips))
## # A tibble: 1 × 3
## Region Purpose Trips
## <chr> <chr> <dbl>
## 1 Sydney Visiting 747.
#(d)
tourism_state <- tourism_ts |>
as_tibble() |>
group_by(State, Quarter) |>
summarise(Trips = sum(Trips), .groups = "drop") |>
as_tsibble(index = Quarter, key = State)
tourism_state
## # A tsibble: 640 x 3 [1Q]
## # Key: State [8]
## State Quarter Trips
## <chr> <qtr> <dbl>
## 1 ACT 1998 Q1 551.
## 2 ACT 1998 Q2 416.
## 3 ACT 1998 Q3 436.
## 4 ACT 1998 Q4 450.
## 5 ACT 1999 Q1 379.
## 6 ACT 1999 Q2 558.
## 7 ACT 1999 Q3 449.
## 8 ACT 1999 Q4 595.
## 9 ACT 2000 Q1 600.
## 10 ACT 2000 Q2 557.
## # ℹ 630 more rows
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. a) Can you spot any seasonality, cyclicity and trend? b) What do you learn about the series? c) What can you say about the seasonal patterns? d) Can you identify any unusual years?
# # us_employment has many job categories mixed together, so I'm
# narrowing down to just "Total Private" -- the one the exercise asks about
total_priv <- us_employment |>
filter(Title == "Total Private")
# is there a long-term trend up or down? Any big dips (recessions)?
total_priv |> autoplot(Employed)
# do all the yearly lines follow a similar shape at the same months?
# That would mean there's a seasonal pattern tied to the calendar.
total_priv |> gg_season(Employed)
# does the average (horizontal line) differ noticeably month to month?
# Confirms whether the seasonal pattern I saw above is real.
total_priv |> gg_subseries(Employed)
#do the points cluster tightly along a diagonal line?
# Tight clustering means the value strongly predicts the next one at that lag.
total_priv |> gg_lag(Employed, geom = "point")
#do the bars spike higher at regular intervals (e.g. every 12 lags)?
# That's numerical confirmation of the seasonality I'm looking for visually above.
total_priv |> ACF(Employed) |> autoplot()
# Bricks remaining plots
aus_production |> gg_season(Bricks)
aus_production |> gg_subseries(Bricks)
aus_production |> gg_lag(Bricks, geom = "point")
aus_production |> ACF(Bricks) |> autoplot()
# Hare (annual data no sub-yearly period, so gg_season() and gg_subseries()
pelt |> autoplot(Hare)
pelt |> gg_lag(Hare, geom = "point")
pelt |> ACF(Hare) |> autoplot()
# H02 from PBS
# PBS is keyed by Concession, Type, and ATC2 filtering ATC2 alone still leaves
# multiple series,we sum across the other keys to get one combined series
h02 <- PBS |>
filter(ATC2 == "H02") |>
summarise(Cost = sum(Cost))
h02 |> autoplot(Cost)
h02 |> gg_season(Cost)
h02 |> gg_subseries(Cost)
h02 |> gg_lag(Cost, geom = "point")
h02 |> ACF(Cost) |> autoplot()
# Barrels
us_gasoline |> autoplot(Barrels)
us_gasoline |> gg_season(Barrels)
us_gasoline |> gg_subseries(Barrels)
us_gasoline |> gg_lag(Barrels, geom = "point")
us_gasoline |> ACF(Barrels) |> autoplot()
“Total Private” Employed (us_employment)
Bricks (aus_production)
Hare (pelt)
H02 Cost (PBS)
Barrels (us_gasoline)