Question 2.1

Use the help function to explore what the series gafa_stock , PBS , vic_elec and pelt represent.

  1. Use autoplot() to plot some of the series in these data sets.
  2. Whatisthetimeintervalofeachseries?
help(gafa_stock)
help(PBS)
help(vic_elec)
help(pelt)

A:

autoplot(gafa_stock)
## Plot variable not specified, automatically selected `.vars = Open`

autoplot(gafa_stock,Volume)

autoplot(gafa_stock,Adj_Close)

#autoplot(PBS,Cost,legend = NULL)
autoplot(vic_elec)
## Plot variable not specified, automatically selected `.vars = Demand`

autoplot(pelt,Hare)

autoplot(pelt,Lynx)

B:

Time Interval of each series:

gafa_range <- c('Range: ',as.character(range(gafa_stock$Date)))
pbs_range <- c('Range: ',as.character(range(PBS$Month)))
vic_range <- c('Range: ',as.character(range(vic_elec$Time)))
pelt_range <- c('Range: ',as.character(range(pelt$Year)))

gafa_range
## [1] "Range: "    "2014-01-02" "2018-12-31"
range(gafa_stock$Date)
## [1] "2014-01-02" "2018-12-31"
ranges <- data.frame(rbind(gafa_range,pbs_range,vic_range,pelt_range))
colnames(ranges) <- c('Range','Minimum','Maximum')

kbl(ranges, longtable = T, booktabs = T, caption = "Ranges of Each Series") %>%
  kable_styling(latex_options = c("repeat_header"))
Ranges of Each Series
Range Minimum Maximum
gafa_range Range: 2014-01-02 2018-12-31
pbs_range Range: 1991 Jul 2008 Jun
vic_range Range: 2012-01-01 00:00:00 2014-12-31 23:30:00
pelt_range Range: 1845 1935

Question 2.2

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

peaks <- gafa_stock %>%
  group_by(Symbol) %>%
  filter(Close == max(Close))

peaks

Question 2.3

tute1 <- read.csv('https://otexts.com/fpp3/extrafiles/tute1.csv')

tute_time_series <- tute1 %>%
  mutate(Quarter = yearquarter(Quarter)) %>%
  as_tsibble(index=Quarter)

tute_time_series %>%
  pivot_longer(-Quarter) %>%
  ggplot(aes(x = Quarter, y = value, colour = name))+
  geom_line()+
  facet_grid(name ~ ., scales = "free_y")

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

  #facet_grid(name ~ ., scales = "free_y")

Facet Grid makes for a much more easy viewing experience, as all of the three plots are separate. This would be most useful in instances where the plots overlap one another. Without Facet Grid enabled for these plots, we see the immense gap between each of the three series.

Question 2.4

library(USgas)
us_total <- USgas::us_total
us_total <- as_tsibble(us_total,index = year,key = state)

ne_states <- us_total %>%
  filter(state == 'Maine' | state == 'Vermont' | state == 'New Hampshire' | state == 'Massachusetts' | state == 'Rhode Island' | state == 'Connecticut')

ne_states %>%
  ggplot(aes(x = year, y = y, colour = state))+
  geom_line()

Question 2.5

tourism <- readxl::read_excel('tourism.xlsx')
tourism <- tourism %>%
  mutate(Quarter = yearquarter(Quarter)) %>%
  as_tsibble(index = Quarter,key = c(Region,State,Purpose))

#tsibble::tourism

head(tourism)
avg_region_purpose <- aggregate(tourism$Trips, list(Region = tourism$Region, Purpose = tourism$Purpose),mean)

colnames(avg_region_purpose) <- c("Region","Purpose","Trips")

max_region_purpose <- avg_region_purpose %>%
  filter(Trips == max(Trips))


kbl(max_region_purpose, longtable = T, booktabs = T, caption = "Maximum Average Overnight Trips") %>%
  kable_styling(latex_options = c("repeat_header"))
Maximum Average Overnight Trips
Region Purpose Trips
Sydney Visiting 747.27 
tourism_state <- tourism %>%
  mutate(Quarter = yearquarter(Quarter)) %>%
  as_tsibble(index = Quarter,key = c(Region,State,Purpose))

tourism_state <- aggregate(tourism_state$Trips, list(State = tourism_state$State),sum)

tourism_state

Question 2.8

set.seed(34)

aus_retail_series <- aus_retail %>%
  filter(`Series ID` == sample(aus_retail$`Series ID`,1))

autoplot(aus_retail_series)
## Plot variable not specified, automatically selected `.vars = Turnover`

gg_season(aus_retail_series)
## Plot variable not specified, automatically selected `y = Turnover`

gg_subseries(aus_retail_series)
## Plot variable not specified, automatically selected `y = Turnover`

gg_lag(aus_retail_series)
## Plot variable not specified, automatically selected `y = Turnover`

aus_retail_series %>%
  ACF(Turnover) %>%
  autoplot()

Year over year, the highest month for turnover is consistently December. The holiday season is the biggest driver of turnover according to the plots.