tutorial for week 8

docs/data/tourism.R

@@ -0,0 +1,100 @@
+library(tsibble)
+library(tidyverse)
+library(lubridate)
+library(ggbeeswarm)
+
+# Data downloaded from Monash A-Z Databases
+# "Tourism Research Australia online for students"
+# Row: Quarter/SA2
+# Column: Stopover reason was Holiday, Visiting friends and relatives, Business, Other reason
+# Sum Overnight trips ('000)
+# Australia: Domestic Overnight Trips ('000) ----
+domestic_trips <- read_csv(
+  "data/domestic_trips_2023-10-08.csv",
+  skip = 9,
+  col_names = c("Quarter", "Region", "Holiday", "Visiting", "Business", "Other", "Total"),
+  n_max = 248056
+) %>% select(-X8)
+
+# fill NA in "Quarter" using the last obs
+fill_na <- domestic_trips %>%
+  fill(Quarter, .direction = "down") %>%
+  filter(Quarter != "Total")
+
+# gather Stopover purpose of visit
+long_data <- fill_na %>%
+  pivot_longer(cols=Holiday:Total,
+               names_to="Purpose",
+               values_to="Trips")
+
+# manipulate Quarter
+qtr_data <- long_data %>%
+  mutate(
+    Quarter = paste(gsub(" quarter", "", Quarter), "01"),
+    Quarter = yearquarter(myd(Quarter))
+  )
+
+# convert to tsibble
+tourism <- qtr_data %>%
+  as_tsibble(key = c(Region, Purpose), index = Quarter)
+usethis::use_data(tourism, overwrite = TRUE, compress = "xz")
+
+saveRDS(tourism, file="data/tourism.rds")
+
+# Standarise the counts
+tourism_max <- tourism |>
+  as_tibble() |>
+  group_by(Region) |>
+  summarise(mx = max(Trips))
+
+tourism_std <- left_join(tourism, tourism_max)
+tourism_std <- tourism_std |>
+  as_tibble() |>
+  mutate(Trips_std = ifelse(mx > 0, 
+                            Trips/mx,
+                            0)) 
+tourism_std |> summarise(m = max(Trips_std))
+tourism_std |> group_by(Region) |> summarise(m = max(Trips_std))
+tourism_std <- tourism_std |>
+  as_tsibble(key = c(Region, Purpose), index = Quarter)
+
+library(feasts)
+tourism_features1 <- tourism_std |>
+  features(Trips_std, list(mean = mean, 
+                           sd = sd))
+tourism_features2 <- tourism_std |>
+  features(Trips_std, feat_stl)
+tourism_features3 <- tourism_std |>
+  features(Trips_std, feat_acf) |>
+  select(-acf1, -acf10)
+
+tourism_features <- bind_cols(tourism_features1, 
+                              tourism_features2[,3:11],
+                              tourism_features3[,3:7]) |>
+  filter(Purpose != "Total") |>
+  mutate(Purpose = factor(Purpose)) |>
+  mutate_if(is.numeric, function(x) ifelse(is.nan(x), 0, x))
+
+tourism_features |>
+  count(Purpose)
+
+library(randomForest)
+tourism_rf <- randomForest(Purpose~., 
+                           data=tourism_features[,-1])
+tourism_rf
+tourism_rf$importance
+
+ggplot(tourism_features, aes(x=mean, y=sd, colour=Purpose)) + 
+  geom_point(alpha=0.5)
+
+tourism_features |>
+  pivot_longer(mean:`season_acf1`, 
+               names_to="var", 
+               values_to="value") |>
+  ggplot(aes(x=Purpose, y=value, colour=Purpose)) +
+    geom_quasirandom() +
+    facet_wrap(~var, ncol=6, scales="free") +
+    xlab("") + ylab("") + 
+    coord_flip() +
+    theme(legend.position="none")
+

docs/sitemap.xml

@@ -6,7 +6,7 @@
   </url>
   <url>
     <loc>https://iml.numbat.space/week8/index.html</loc>
-    <lastmod>2024-02-05T21:28:13.682Z</lastmod>
+    <lastmod>2024-04-20T06:01:33.376Z</lastmod>
   </url>
   <url>
     <loc>https://iml.numbat.space/week7/slides.html</loc>
@@ -38,7 +38,7 @@
   </url>
   <url>
     <loc>https://iml.numbat.space/week4/index.html</loc>
-    <lastmod>2024-03-15T04:09:22.102Z</lastmod>
+    <lastmod>2024-04-19T00:32:10.657Z</lastmod>
   </url>
   <url>
     <loc>https://iml.numbat.space/week3/slides.html</loc>

docs/week4/index.html

@@ -194,7 +194,6 @@ <h2 id="toc-title">On this page</h2>
   <li><a href="#lecture-slides" id="toc-lecture-slides" class="nav-link" data-scroll-target="#lecture-slides">Lecture slides</a></li>
   <li><a href="#tutorial-instructions" id="toc-tutorial-instructions" class="nav-link" data-scroll-target="#tutorial-instructions">Tutorial instructions</a></li>
   <li><a href="#assignments" id="toc-assignments" class="nav-link" data-scroll-target="#assignments">Assignments</a></li>
-  <li><a href="#assignments-1" id="toc-assignments-1" class="nav-link" data-scroll-target="#assignments-1">Assignments</a></li>
   </ul>
 </nav>
     </div>
@@ -253,9 +252,6 @@ <h2 class="anchored" data-anchor-id="tutorial-instructions">Tutorial instruction
 </section>
 <section id="assignments" class="level2">
 <h2 class="anchored" data-anchor-id="assignments">Assignments</h2>
-</section>
-<section id="assignments-1" class="level2">
-<h2 class="anchored" data-anchor-id="assignments-1">Assignments</h2>
 <ul>
 <li><a href="../assignments/assign01.zip">Assignment 1</a> is due on Friday 22 March.</li>
 <li><a href="../assignments/assign02.zip">Assignment 2</a> is due on Friday 12 April.</li>