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 1.3.0
## ✔ 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(ggplot2)
library(completejourney)
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(RColorBrewer)
library(lubridate)
transactions <- transactions_sample
Plot 1
transactions %>%
inner_join(products, by = "product_id") %>%
inner_join(demographics, by = "household_id") %>%
group_by(product_type) %>%
filter(kids_count > 0) %>%
summarise(total_sales = sum(sales_value)) %>%
arrange(desc(total_sales)) %>% #Top 5 product types that families with kids purchase are GASOLINE-REG UNLEADED, FLUID MILK WHITE ONLY, SOFT DRINKS 12/18&15PK CAN CAR, BEERALEMALT LIQUORS, CHOICE BEEF
filter(str_detect(product_type, regex("GASOLINE-REG UNLEADED|FLUID MILK WHITE ONLY|SOFT DRINKS 12/18&15PK CAN CAR|BEERALEMALT LIQUORS|CHOICE BEEF", ignore_case = TRUE))) %>%
ggplot(aes(x = product_type, y = total_sales)) +
geom_col() +
scale_x_discrete("Product Types") +
scale_y_continuous("Total Sales", labels = scales::dollar) +
ggtitle("Top 5 Products That Families With Kids Purchase",
subtitle = "Households with one or more children spend the most on gasoline") +
theme_minimal() +
coord_flip()

Plot 2
products %>%
filter(str_detect(product_category, "DOG FOODS")) %>%
inner_join(transactions, by = 'product_id') %>%
inner_join(demographics, by = 'household_id') %>%
ggplot(aes(x = quantity, y = product_type)) +
geom_point(aes(color = income)) +
scale_color_brewer(palette="Set3") +
labs(
title = "Dog Food Products Quantity Purchased By Income Groups",
subtitle = "Interestingly, the 50-74K income bracket buys the most gourmet dog foods",
x = "Quantity Purchased",
y = "Different Product Types of Dog Foods" ) +
theme(plot.margin = margin(t = 30, r = 30, b = 30, l = 30, unit = "pt")) +
theme(axis.text.y = element_text(size = 6))

Plot 3
transactions %>%
inner_join(products, by = "product_id") %>%
inner_join(demographics, by = "household_id") %>%
filter(str_detect(product_category, "PIZZA")) %>%
mutate(transaction_date = date(transaction_timestamp)) %>%
mutate(transaction_month = month(transaction_timestamp, label = TRUE)) %>%
group_by(transaction_date, age) %>%
summarise(total_sales = sum(sales_value)) %>%
ggplot(aes(x = transaction_date, y = total_sales, color = age)) +
scale_color_brewer(palette = "Set3") +
geom_smooth(se = FALSE) +
scale_y_continuous(name = "Total Sales", labels = scales::dollar) +
labs(title = "Total Sales of Pizza Products by Age Groups Across The Year",
subtitle = "Seasonal trends in pizza sales are subtle across age groups during the year",
x = "Month",
y = "Total Sales",
color = "Age")
## `summarise()` has grouped output by 'transaction_date'. You can override using
## the `.groups` argument.
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
