R Notebook

knitr::opts_chunk$set(echo = TRUE)
library(completejourney)
library(tidyverse)
library(scales)
library(dplyr)

transactions <- transactions_sample
transactions

#First Chart

top_products <- transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(income, product_id, product_category) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE), .groups = "drop") %>%
  arrange(income, desc(total_sales)) %>%
  group_by(income) %>%
  slice_head(n = 5)


ggplot(top_products, aes(x = total_sales, y = product_category, fill = income)) +
  geom_col() +
  facet_wrap(~income, scales = "free_y", ncol = 2) +
  labs(
    title = "Top 5 Purchased Products by Five Lowest Income Level",
    subtitle = "Comparing product preferences across income categories",
    x = "Total Sales ($)",
    y = "Product Category",
    fill = "Income Level"
  ) +
  theme_minimal()

#Second Chart

cookies_cones <- transactions %>%
  inner_join(products, by = 'product_id') %>%
  filter(product_category == "COOKIES/CONES") %>%  
  inner_join(demographics, by = "household_id") %>%
  group_by(income) %>%
  summarise(total_cookies_cones_purchased = sum(quantity, na.rm = TRUE), .groups = "drop") %>%
  arrange(income)

ggplot(data = cookies_cones, aes(x = income, y = total_cookies_cones_purchased, fill = income)) + 
  geom_col() +
  labs(
    title = "Cookies/Cones Purchases by Income Level",
    subtitle = "Total quantity of cookies/cones purchased across different income levels",
    x = "Income Level",
    y = "Total Quantity of Cookies/Cones Purchased"
  ) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) 

#Third Chart

discount_effectiveness <- transactions %>%
  inner_join(products, by = "product_id") %>%
  mutate(discounted = ifelse(coupon_disc > 0 | retail_disc > 0, "Discounted", "Full Price")) %>%
  group_by(department, discounted) %>%
  summarize(count = n(), .groups = "drop") %>%
  mutate(pct = count / sum(count) * 100) %>%
  filter(discounted == "Discounted") %>%
  arrange(desc(pct)) %>%
  slice_max(pct, n = 12) 

ggplot(discount_effectiveness, aes(x = reorder(department, pct), y = pct, fill = pct)) +
  geom_col() +
  coord_flip() +
  labs(
    title = "Discount usage by each department",
    x = "Department",
    y = "Percentage of Transactions Using a Discount (%)",
    caption = "The study has been limited to the first 12 categories with the highest %discount usage",
    fill = "Discount Usage (%)"
  ) +
  theme_minimal() + 
  theme(
    plot.title = element_text(size = 12, face = "bold", margin = margin(b = 20)),
    strip.text = element_text(size = 9, face = "bold"),
    plot.caption = element_text(size = 7, hjust = 0, margin = margin(t = 30)),
    axis.title.x = element_text(margin = margin(t = 15)),  
    axis.title.y = element_text(margin = margin(r = 10))  
  )