Module 5 Visual Lab

First Graph

merged_data_1 <- coupons %>%
  inner_join(products, by = "product_id")

summary_data_1 <- merged_data_1 %>%
  group_by(department) %>%
  summarize(num_coupons = n()) %>%
  arrange(desc(num_coupons)) %>%
  slice_max(order_by = num_coupons, n = 10)

ggplot(summary_data_1, aes(x = reorder(department, num_coupons), y = num_coupons, fill = department)) +
  geom_bar(stat = "identity") +
  labs(title = "Top 10 Departments with Most Coupons",
       x = "Department",
       y = "Number of Coupons") +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
    axis.text.y = element_text(angle = 45, hjust = 1),
        legend.position = "none") +
  coord_flip() +
  scale_fill_brewer(palette = "Set3")

Second Graph

grocery_transactions <- transactions %>%
  inner_join(products, by = "product_id") %>%
  filter(department == "GROCERY")

merged_data_2 <- grocery_transactions %>%
  inner_join(demographics, by = "household_id")
summary_data_2 <- merged_data_2 %>%
  mutate(week = as.integer(format(transaction_timestamp, "%U"))) %>%
  group_by(week, kids_count) %>%
  summarize(num_transactions = n())

ggplot(summary_data_2, aes(x = week, y = num_transactions, color = factor(kids_count))) +
  geom_line(size = 1.2) +
  geom_point(size = 2) +
  xlim(0, 52) +
  scale_color_brewer(palette = "Set1") +
  labs(title = "Total Grocery Department items sold per Week",
       subtitle="Sorted on the amount of kids the Customers have",
       x = "Week",
       y = "Number of Items Purchased",
       color = "Number of Kids") +
  theme_minimal() +
  theme(
    plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
    axis.title = element_text(size = 14),
    axis.text = element_text(size = 12),
    legend.title = element_text(size = 12),
    legend.text = element_text(size = 10)
  )

Third Graph

transactions <- transactions %>%
  left_join(products, by = "product_id") %>%
  left_join(promotions_sample, by = "product_id")

summary_data_3 <- transactions %>%
  group_by(display_location, product_category) %>%
  summarise(total_purchases = n()) %>%
  ungroup() %>%
  arrange(display_location, desc(total_purchases))


store_front_data <- summary_data_3 %>%
  filter(display_location == "1") %>%
  top_n(10, total_purchases)


ggplot(store_front_data, aes(x = reorder(product_category, total_purchases), y = total_purchases, fill = product_category)) +
  geom_bar(stat = "identity") +
  coord_flip() +
  scale_fill_brewer(palette = "Paired") +
  labs(title = "      Top 10 Purchased Product Catagories
                Displayed at the Store Front", x = "Product Category", y = "Total Purchases") +
  theme_minimal() +
  theme(legend.position = "none")