Module 5 Lab

library(completejourney)

Welcome to the completejourney package! Learn more about these data sets at http://bit.ly/completejourney.

library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(ggplot2)
library(forcats)
library(lubridate)

Attaching package: ‘lubridate’

The following objects are masked from ‘package:base’:

    date, intersect, setdiff, union

library(stringr)

Visualization 1

transactions <- get_transactions()
top_products <-transactions %>%
  inner_join(products, by = 'product_id') %>%
  inner_join(demographics, by= 'household_id') %>%
  group_by(income,product_category) %>%
  summarize(total_quantity = sum(quantity, na.rm = TRUE)) %>%
  arrange(income, desc(total_quantity) <=5) %>%
  group_by(income) %>%
  slice_head(n = 5)

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

ggplot(top_products, aes(x = reorder(product_category, total_quantity), y = total_quantity, fill = income)) +
  geom_col() +
  coord_flip()+
  facet_wrap(~ income, scales = "free") +
  labs(
    title = "Top 5 Most Purchased Products by Income Level",
    subtitle = "Income levels drive different purchasing preferences",
    x = "Product Category",
    y = "Total Quantity Purchased",
  ) +
  theme_minimal() +
  theme(
    axis.text.y = element_text(size = 5),  
    strip.text = element_text(size = 8, face = "bold"),  
    plot.title = element_text(size = 7, face = "bold"), 
    plot.subtitle = element_text(size = 6),
    axis.text.x  = element_text(size = 5),
    legend.position = "bottom",
    legend.text = element_text(size = 6)
  ) 

NA

Visualization 2

transactions <- get_transactions()
products %>%
  filter(product_category == "DEODORANTS", 
         str_detect(product_type, "AEROSOL DEODORANTS"))  %>%
  inner_join(transactions) %>%
  mutate(month = month(transaction_timestamp)) %>%
  group_by(month) %>%
  summarize(sales_per_month= sum(sales_value)) %>%
  ggplot(aes(month,sales_per_month))+
  geom_line(stat='identity', 
            color = "lavender", 
            size = 2) +
  geom_point(size = 3) +
  ggtitle("2017 Aerosol Deodorants Sales Per Month",
          subtitle = "The average sales per month is $85 and peaked in Oct with $109 monthly sales ")+   
  scale_y_continuous("Total Aerosol Deodorants Sales", 
                     label = scales::dollar) +
  scale_x_continuous("Month",
                     limits = c(1,12),
                     breaks = c(1,2,3,4,5,6,7,8,9,10,11,12),
                     labels = c("Jan","Feb","March","April","May","June","July",
                                "Aug","Sept","Oct","Nov","Dec"))+ 
  theme_classic()

Joining with `by = join_by(product_id)`Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
Please use `linewidth` instead.

Visualization 3

transactions <- get_transactions()
transactions %>%
  group_by(household_id) %>%
  summarise(
    total_sales = sum(sales_value, na.rm = TRUE),
    total_items = sum(quantity, na.rm = TRUE),
    .groups = "drop"
  ) %>%
  
  ggplot(aes(x = total_items, y = total_sales)) +
  geom_point(alpha = 0.5, color = "blue") +  
  geom_smooth(method = "lm", color = "red", se = FALSE) + 
  labs(
    title = "Relationship Between Total Sales and Number of Items Purchased",
    subtitle = "There is a linear relationship between total sales and quantity purchased",
    x = "Total Items Purchased",
    y = "Total Sales ($)"
  ) +
  scale_x_continuous("Total Items Purchased",
                     limits = c(1,1500),
  ) +
  scale_y_continuous("Total Sales",
                     label = scales::dollar,
                     limits = c(1,3500)
                     ) +
  theme_minimal()