##Run this code before every visual

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 1.9.3     ✔ 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.
library(completejourney)
library(tidyverse)
library(dplyr)
library(lubridate)
library(ggplot2)


transactions <- get_transactions()


demographics <- demographics %>%
  mutate(income_level = as.character(income))

complete_data <- transactions %>%
  inner_join(demographics, by = "household_id") %>%
  inner_join(products, by = "product_id")

##Visual 1

products %>%
  filter(str_detect(product_category, regex("(MEAT)"))) %>%
  inner_join(transactions_sample, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(age) %>%
  summarize(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  ggplot(aes(x = factor(age), y = total_sales)) +  
  geom_col() +
  scale_y_continuous("Total Sales (Meat)", labels = scales::dollar) +
  scale_x_discrete("Age Group") +  
  ggtitle("Age Group spends most on Meat",
          subtitle = "Meat sales per Age Group")

##Visual 2

# Join datasets
complete_data <- transactions %>%
  inner_join(demographics, by = "household_id") %>%
  inner_join(products, by = "product_id")

# Summarize data for pie chart (count of purchases by age group)
age_summary <- complete_data %>%
  group_by(age) %>%
  summarize(total_purchases = n(), .groups = 'drop') %>%
  mutate(percentage = total_purchases / sum(total_purchases) * 100)

# Create pie chart
pie_chart <- ggplot(age_summary, aes(x = "", y = percentage, fill = age)) +
  geom_bar(stat = "identity", width = 1) +
  coord_polar("y") +
  labs(title = "Percentage of Total Purchases by Age Group",
       subtitle = "Distribution of Purchases Made Across Different Age Groups",
       fill = "Age Group") +
  geom_text(aes(label = paste0(round(percentage, 1), "%")), 
            position = position_stack(vjust = 0.5), 
            color = "white") +  # Adding percentage labels on the pie chart
  theme_void() +
  theme(legend.position = "right")

# Render the pie chart
print(pie_chart)

##Visual 3

# Filter the products dataset for alcohol-related products
alcohol_products <- products %>%
  filter(str_detect(tolower(department), "alcohol") | str_detect(tolower(product_category), "beer|wine|spirits"))

# Join transactions with filtered alcohol products
alcohol_sales <- transactions %>%
  inner_join(alcohol_products, by = "product_id")

# Summarize sales value by day of the week
alcohol_sales_by_day <- alcohol_sales %>%
  mutate(day_of_week = wday(transaction_timestamp, label = TRUE, abbr = FALSE)) %>%  # Extract day of week
  group_by(day_of_week) %>%
  summarize(total_sales_value = sum(sales_value), .groups = 'drop')

# Create a bar plot for Alcohol Sales Value by Day
alcohol_sales_plot <- ggplot(alcohol_sales_by_day, aes(x = day_of_week, y = total_sales_value)) +
  geom_col(fill = "dodgerblue") +
  labs(title = "Alcohol Sales Value by Day of the Week",
       subtitle = "Total Alcohol Sales for Each Day",
       x = "Day of the Week",
       y = "Total Sales Value ($)") +
  theme_minimal()

# Render the plot
print(alcohol_sales_plot)