Week5_lab_Pushpapriya

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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.

# Load datasets
transactions <- transactions_sample
products <- products
demographics <- demographics
coupon_redemptions <- coupon_redemptions
campaigns <- campaigns
campaign_descriptions <- campaign_descriptions

Plot 1:- Higher income households spend more on premium products

transactions %>%
  inner_join(products, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(income, product_category) %>%
  summarise(total_sales = sum(sales_value), .groups = "drop") %>%
  group_by(income) %>%
  slice_max(total_sales, n = 5) %>%
  ggplot(aes(x = reorder(product_category, total_sales),
             y = total_sales,
             fill = income)) +

  geom_col() +

  coord_flip() +

  labs(
    title = "Premium Product Spending is Dominated by Higher-Income Households",
    subtitle = "Top 5 product categories by total sales within each income group",
    x = "Product Category",
    y = "Total Sales ($)",
    fill = "Income Level",
    caption = "Source: CompleteJourney Dataset"
  ) +

  theme_minimal(base_size = 14)

Plot 2:- Coupon campaigns increase spending

transactions %>%
  inner_join(coupon_redemptions, by = "household_id", relationship = "many-to-many") %>%
  inner_join(campaigns, by = c("household_id", "campaign_id"), relationship = "many-to-many") %>%
  inner_join(campaign_descriptions, by = "campaign_id") %>%
  group_by(campaign_type) %>%
  summarise(total_sales = sum(sales_value), .groups = "drop") %>%

  ggplot(aes(x = campaign_type,
             y = total_sales,
             fill = campaign_type)) +

  geom_col() +

  labs(
    title = "Campaign Type Strongly Influences Customer Spending Behavior",
    subtitle = "Households exposed to different campaign types generate varying total sales",
    x = "Campaign Type",
    y = "Total Sales ($)",
    fill = "Campaign Type",
    caption = "Source: CompleteJourney Dataset"
  ) +

  theme_minimal(base_size = 14)

Plot 3:-Family size influences spending

transactions %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(household_size) %>%
  summarise(total_sales = sum(sales_value), .groups = "drop") %>%
  ggplot(aes(x = household_size,
             y = total_sales,
             fill = household_size)) +

  geom_col() +

  labs(
    title = "Larger Households Spend Significantly More on Groceries",
    subtitle = "Total grocery spending by household size",
    x = "Household Size",
    y = "Total Sales ($)",
    fill = "Household Size",
    caption = "Source: CompleteJourney Dataset"
  ) +

  theme_minimal(base_size = 14)

```