Lab 5

library(completejourney)
library(tidyverse) 

top_products_income <- transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(income, product_id) %>%
  summarise(total_sales = sum(sales_value), .groups = 'drop') %>%
  arrange(desc(total_sales)) %>%
  slice_max(order_by = total_sales, n = 5, by = "income")

ggplot(top_products_income, aes(x = reorder(product_id, total_sales), y = total_sales, fill = income)) + geom_bar(stat = “identity”, position = position_dodge()) + labs(title = “Top 5 Products Purchased by Different Income Levels”, subtitle = “Comparison of product preferences across income brackets”, x = “Product Description”, y = “Total Sales Value”, fill = “Income Bracket”) + theme_minimal() + theme(axis.text.x = element_text(angle = 45, hjust = 1))

transactions$discount <- transactions$retail_disc + transactions$coupon_disc + transactions$coupon_match_disc

discount_analysis <- transactions %>%
  inner_join(products, by = "product_id") %>%
  group_by(product_category) %>%
  summarise(avg_discount = mean(discount, na.rm = TRUE), .groups = 'drop') %>%
  arrange(desc(avg_discount)) %>%
  slice_max(order_by = avg_discount, n = 5)  

ggplot(discount_analysis, aes(x = reorder(product_category, avg_discount), y = avg_discount, fill = product_category)) + geom_bar(stat = “identity”) + coord_flip() +
labs(title = “Top 5 Most Discounted Product Categories”, subtitle = “Average discount applied across product categories”, x = “Product Category”, y = “Average Discount ($)”) + theme_minimal() + theme(legend.position = “none”)

store_spending <- transactions %>%
  group_by(store_id) %>%
  summarise(total_spending = sum(sales_value, na.rm = TRUE), .groups = 'drop') %>%
  top_n(n = 25, wt = total_spending)  

ggplot(store_spending, aes(x = reorder(store_id, -total_spending), y = total_spending, fill = total_spending)) + geom_col() + coord_flip() +
scale_fill_gradient(low = “lightblue”, high = “darkblue”) +
labs(title = “Customer Spending by Top 25 Store Locations”, subtitle = “Total sales value at the top 25 store locations”, x = “Store ID”, y = “Total Spending ($)”) + theme_minimal() + theme(axis.text.y = element_text(size = 8))