# All Library functions for packages
library(completejourney)
## Warning: package 'completejourney' was built under R version 4.2.3
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.2.3
## Warning: package 'ggplot2' was built under R version 4.2.3
## Warning: package 'tibble' was built under R version 4.2.3
## Warning: package 'tidyr' was built under R version 4.2.3
## Warning: package 'readr' was built under R version 4.2.3
## Warning: package 'purrr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## Warning: package 'forcats' was built under R version 4.2.3
## Warning: package 'lubridate' was built under R version 4.2.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ 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)
# Data variables
prod <- products
transactions <- get_transactions()
d <- demographics
prom <- get_promotions()
c <- coupons
prod %>%
filter(product_category == "COFFEE")%>%
count(product_type)
## # A tibble: 17 × 2
## product_type n
## <chr> <int>
## 1 AUTHENTIC DRY BEVERAGES W/O SW 1
## 2 DECAF BEAN: FLAVORED 3
## 3 DECAF BEAN: REGULAR 11
## 4 FLAVORED BEAN COFFEE 30
## 5 GROUND COFFEE 186
## 6 GROUND DECAFFINATED 35
## 7 GROUND FLVR DECAF COFFEE 19
## 8 GROUND FLVR REG COFFEE 56
## 9 INSTANT COFFEE FLAVORED NO SWE 63
## 10 INSTANT COFFEE FLAVORED W/SWEE 37
## 11 INSTANT COFFEE REGULAR 30
## 12 INSTANT DECAF FLVR COFFEE W/ S 5
## 13 INSTANT DECAFFINATED 12
## 14 INSTANT TEA & TEA MIX 1
## 15 MOLASSES & SYRUPS 2
## 16 NON DAIRY CREAMER: DRY 67
## 17 REGULAR BEAN 46
# First graph
transactions %>%
inner_join(prod, by = "product_id")%>%
inner_join(d, by = "household_id")%>%
mutate(total_sales = sum(sales_value))%>%
filter(department == "GROCERY")%>%
ggplot()+
geom_col(aes(x = department, y = total_sales, fill = income))+
labs(title = "Which Income Range Purchases the Most Groceries?",
subtitle = "Grocery Sales by Income Range",
x = "",
y = "Total Sales")+
scale_y_continuous(labels = c("0","250 Billion", "500 Billion", "750 Billion", "1 Trillion"),
breaks = c(0,250000000000, 500000000000,750000000000, 1000000000000))
# Second Graph
transactions %>%
inner_join(prod, by = "product_id")%>%
inner_join(d, by = "household_id")%>%
mutate(month = month(transaction_timestamp))%>%
mutate(total_sales = sum(sales_value))%>%
ggplot()+
geom_col(aes(x = month, y = total_sales, fill = age))+
scale_x_continuous(name = "Month",
labels = c("Jan", "Feb", "Mar", "Apr", "May",
"Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"),
breaks = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12))+
scale_y_continuous(name = "Total Sales",
labels = c("0", "50 Billion", "100 Billion", "150 Billion", "200 Billion"),
breaks = c(0, 50000000000, 100000000000, 150000000000, 200000000000))+
ggtitle("Total Monthly Sales by Age Group")
# Third Graph
d %>%
inner_join(transactions, by = "household_id")%>%
mutate(total_sales = sum(sales_value))%>%
na.omit(marital_status)%>%
ggplot()+
geom_col(aes(x = household_size, y = total_sales, fill = marital_status))+
labs(title = "Total Sales by Household Size and Marital Status",
x = "Household Size",
y = "Total Sales",
fill = "Marital Status")+
scale_y_continuous(labels = c("0", "200 Billion", "400 Billion"),
breaks = c(0, 200000000000, 400000000000) )
