Module 5 Lab

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(completejourney)

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

transactions <- get_transactions()
transactions

demographics <- completejourney::demographics
products <- completejourney::products

fruit_veg <- products %>%
  filter(str_detect(product_category, "VEGETABLES|FRUIT"))

fruit_veg_purchases <- transactions %>%
  inner_join(fruit_veg, by = "product_id") %>%
  inner_join(demographics, by = "household_id")

marital_purchases <- fruit_veg_purchases %>%
  group_by(marital_status) %>%
  summarise(count = n()) %>%
  mutate(percentage = count / sum(count) * 100) %>%
  arrange(desc(count))

ggplot(marital_purchases, aes(x = marital_status, y = percentage, fill = marital_status)) +
  geom_col(color = "black") +
  labs(title = "Proportion of Fruit & Vegetable Purchases by Marital Status",
       x = "Marital Status",
       y = "Percentage of Purchases (%)") +
  theme_minimal() +
  scale_fill_brewer(palette = "Set2")

vegetables <- products %>%
  filter(str_detect(product_category, "VEGETABLES"))

vegetable_purchases <- transactions %>%
  inner_join(vegetables, by = "product_id")

vegetable_purchases <- vegetable_purchases %>%
  mutate(purchase_time = hms:: as_hms(transaction_timestamp),
         purchase_hour = hour(transaction_timestamp))

hourly_purchases <- vegetable_purchases %>%
  group_by(purchase_hour) %>%
  summarise(count = n()) %>%
  arrange(desc(count))

ggplot(hourly_purchases, aes(x = purchase_hour, y= count)) +
  geom_col(fill = "lightgreen", color = "black") +
  scale_x_continuous(breaks = seq(0,23, by = 1)) +
  labs(title = "Most Popular Time to Buy Vegetables",
       x = "Hour of the Day",
       y= "Number of Transactions") +
  theme_minimal()

household_purchases <- transactions %>%
  group_by(household_id) %>%
  summarise(total_quantity = sum(quantity))

age_quantity_data <- demographics %>%
  select(household_id, age) %>%
  inner_join(household_purchases, by = "household_id")

ggplot(age_quantity_data, aes(x = age, y = total_quantity, color = age)) +
  geom_jitter(width = 0.2, alpha = 0.6) +  # Jitter points to prevent overlap
  labs(title = "Relationship Between Age and Quantity of Products Bought",
       x = "Age Range",
       y = "Total Quantity of Products Bought") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))