Week 5 Lab

library(completejourney)

## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.

library(ggplot2)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

data1 <- transactions_sample %>%
  inner_join(demographics, by = "household_id")

income_sales <- data1 %>%
  group_by(income) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE))

ggplot(income_sales, aes(x = income, y = total_sales, fill = income)) +
  geom_bar(stat = "identity") +
  labs(title = "Total Sales by Household Income",
       x = "Household Income",
       y = "Total Sales Value") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

data3 <- coupon_redemptions %>%
  inner_join(demographics, by = "household_id")

coupon_age <- data3 %>%
  group_by(age) %>%
  summarise(total_redemptions = n())

ggplot(coupon_age, aes(x = age, y = total_redemptions, fill = age)) +
  geom_bar(stat = "identity") +
  labs(title = "Total Coupon Redemptions by Age Group",
       x = "Age Group",
       y = "Total Coupon Redemptions") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

data4 <- transactions_sample %>%
  inner_join(products, by = "product_id")

category_sales <- data4 %>%
  group_by(product_category) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  arrange(desc(total_sales)) %>%
  slice(1:10)  

ggplot(category_sales, aes(x = reorder(product_category, -total_sales), y = total_sales)) +
  geom_point(size = 4, color = "steelblue") +
  labs(title = "Total Sales by Product Category (Top 10)",
       x = "Product Category",
       y = "Total Sales Value") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))