Week 5 Lab - Kyle Rex

library(ggplot2)
library(dplyr)
library(completejourney)

Which Age Group Buys the Most Cookies

The 45-54 Age Group spends the most on cookies

transactions <- get_transactions()
transactions_with_demo <- transactions %>%
  inner_join(demographics, by = "household_id")
demo_products <- transactions_with_demo %>%
  inner_join(products, by = "product_id")
cookie_purchases <- filter(demo_products, product_category == "COOKIES/CONES")
cookies_by_age <- cookie_purchases %>%
  group_by(age) %>%
  summarise(total_spend = sum(sales_value, na.rm = TRUE))
ggplot(data = cookies_by_age, aes(x = age, y = total_spend)) +
  geom_bar(stat = "identity", fill = "lightblue") +
  labs(title = "Cookies Purchases by Age Group", 
       x = "Age Group", 
       y = "Spending on Cookies")

Average Spending on Top Categories by Marital Status

Married Couples spend marginally more and spend it on Miscellaneous items or Beef most commonly

joined_data <- transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id")
category_spending_by_marital_status <- joined_data %>%
  filter(!is.na(marital_status)) %>%
  group_by(marital_status, product_category)%>%
  summarise(total_spend = sum(sales_value, na.rm = TRUE), num_trips = n()) %>%
  mutate(avg_spend_per_trip = total_spend / num_trips)

`summarise()` has grouped output by 'marital_status'. You can override using the `.groups` argument.

top_5_categories_by_spend <- category_spending_by_marital_status %>%
  group_by(marital_status) %>%
  slice_max(total_spend, n = 5)
ggplot(top_5_categories_by_spend, aes(x = product_category, y = marital_status, fill = avg_spend_per_trip)) +
  geom_tile(color = "white") +
  scale_fill_gradient(low = "lightyellow", high = "red", name = "Avg Spend per Trip") +
  labs(title = "Average Spend per Trip on Top 5 Categories by Marital Status",
       subtitle = "Heatmap of average spend per trip for top product categories",
       x = "Product Category",
       y = "Marital Status") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Coffee Spending by Income Level

The mean spending on coffee increases with increases in Income but it there are quite a few lower income outliers

coffee_data <- joined_data %>%
  filter(product_category == "COFFEE")
ggplot(coffee_data, aes(x = income, y = sales_value, fill = income)) +
  geom_boxplot(outlier.color = "red", outlier.shape = 16, outlier.size = 2) +
  labs(title = "Distribution of Spending on Coffee by Income Level",
       subtitle = "Box plot showing coffee spending across income levels",
       x = "Income Level",
       y = "Spending on Coffee (USD)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))