Module_5_Visualization_Lab_Allen_Dowds

library(completejourney)

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

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

Distinct Plot 1

products %>%
  filter(str_detect(product_category, regex("(CANDY)"))) %>%
  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 = age, y = total_sales)) +
    geom_col() +
  scale_y_continuous("Total Sales for Candy", labels = scales::dollar) +
  scale_x_discrete("Age") +  
  ggtitle("Which Age Group Has the Biggest Sweet Tooth?",
          subtitle = "Age group '45-54' spends the most on candy")

Distinct Plot 2

products %>%
  inner_join(transactions_sample, by = "product_id") %>%
  filter(str_detect(department, regex("(PRODUCE)"))) %>%
  group_by(product_category) %>%
  summarize(coupon_sales =sum(coupon_disc, na.rm = TRUE)) %>%
  ggplot(aes(x = coupon_sales, y = fct_reorder(product_category, coupon_sales)))+
  geom_point(color = "red") +
  labs(title = "Total Coupon Spend On Produce",
       subtitle = "Salad Mix had the most coupons presented",
       x = "Total Coupon Sales",
       y = "Produce Item")

Distinct Plot 3

transactions_sample %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(household_size, income) %>%
  summarize(total_spend = sum(sales_value, na.rm = TRUE)) %>%
  ggplot(aes(x = household_size, y = total_spend)) +
  scale_y_continuous("Total Spent", labels = scales::dollar) +
  geom_col() +
  scale_x_discrete("Household Size") +  
  facet_wrap(~income) +
  ggtitle("Which household size spends the most?",
          subtitle = "Consumers with households of 2, in the 50-74k range, spend the most ")

## `summarise()` has grouped output by 'household_size'. You can override using
## the `.groups` argument.