Meesha Tanna - Module 5 Lab

library(tidyverse)

── Attaching core tidyverse packages ────────────────
✔ 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 ]8;;http://conflicted.r-lib.org/conflicted package]8;; 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.

avg_product_sales <- transactions %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(product_id, age) %>%
  summarize(total_product_sales = sum(sales_value, na.rm = TRUE)) %>%
  group_by(age) %>%
  summarize(avg_sales_value = mean(total_product_sales, na.rm = TRUE))

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

  ggplot(data = avg_product_sales, aes(x = avg_sales_value, y = age)) + 
    geom_point(color = "darkseagreen4") +
    labs(
      title = "Average Product Sales by Age",
      x = "Average Product Sales",
      y = "Age")

NA

# Plot 2: Top 10 Categories Sold
top_ten_categories <- transactions %>%
  inner_join(products, by = "product_id") %>%
  group_by(product_category) %>%
  summarize(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  arrange(desc(total_sales)) %>%
  slice_head(n = 10)

ggplot(data = top_ten_categories, aes(x = reorder(product_category, total_sales), y = total_sales)) + 
  geom_bar(stat = "identity", color = "coral1") +
  coord_flip() +
  scale_y_continuous(labels = scales::comma) +
  labs(
    title = "Top 10 Product Categories Sold",
    x = "Product Category",
    y = "Total Sales"
  )

# Plot 3: Total Number of Snacks per Household Size
snacks_household <- transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  filter(!is.na(product_category) == "BAG SNACKS") %>%
  group_by(household_size) %>%
  summarize(total_snacks_sales = sum(sales_value, na.rm = TRUE)) 
  ggplot(snacks_household, aes(x = household_size, y = total_snacks_sales)) +
    geom_col(color = "darkviolet") +
    labs(
      title = "Total Number of Snacks per Household Size",
      x = "Household Size",
      y = "Total Snack Sales"
    )