Module 5 Lab Visualization

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   3.4.4     ✔ 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.

## Visualization 1
products %>%
  filter(str_detect(product_category, regex("(VITAMINS)"))) %>%
  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 for Vitamins", labels = scales::dollar) +
  scale_x_discrete("Age") +  
  ggtitle("Which Age Group Spends the Most on Vitamins?",
          subtitle = "People aged 45-54 spend the most money on Vitamins")

## Visualization 2
demographics %>%
  inner_join(completejourney::transactions_sample, by = "household_id") %>%
  group_by(marital_status, income) %>%
  summarize(total_retail_disc = sum(retail_disc, na.rm = TRUE)) %>%
  ggplot(aes(x = marital_status, y = total_retail_disc)) +  
  geom_col() +
  scale_y_continuous("Total Retail Discount", labels = scales::dollar) +
  scale_x_discrete("Marital Status") +  
  facet_wrap(~income) +
  ggtitle("Who uses the most Retail Discounts?",
          subtitle = "Unmarried Households with income ranging from $50-74k use the most retail discounts") 

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

## Visualization 3
demographics %>%
  inner_join(completejourney::transactions_sample, by = "household_id") %>%
  group_by(household_size, income) %>%
  summarize(total_coupon_disc = sum(coupon_disc, na.rm = TRUE)) %>%
  ggplot(aes(x = household_size, y = total_coupon_disc)) +  
  geom_col() +
  scale_y_continuous("Total Coupon Discount", labels = scales::dollar) +
  scale_x_discrete("Household Size") +  
  facet_wrap(~income) +
  ggtitle("Which household size uses the most coupons?",
          subtitle = "Households sizes of 2 with income in the range of 50-74k use the most coupons ")

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