hw6

Step 1: Load necessary libraries

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.1     ✔ stringr   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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

Step 2: Read the RDS file

bike_orderlines <- readRDS("bike_orderline.rds")

Step 3: Check the column names

glimpse(bike_orderlines)

## Rows: 15,644
## Columns: 15
## $ order_date     <dttm> 2011-01-07, 2011-01-07, 2011-01-10, 2011-01-10, 2011-0…
## $ order_id       <dbl> 1, 1, 2, 2, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 6, 6, 6, 6, 7…
## $ customer_id    <dbl> 2, 2, 10, 10, 6, 6, 6, 6, 6, 22, 8, 8, 8, 8, 16, 16, 16…
## $ product_id     <dbl> 48, 52, 76, 52, 2, 50, 1, 4, 34, 26, 96, 66, 35, 72, 45…
## $ order_line     <dbl> 1, 2, 1, 2, 1, 2, 3, 4, 5, 1, 1, 2, 3, 4, 1, 2, 3, 4, 1…
## $ quantity       <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1…
## $ price          <dbl> 6070, 5970, 2770, 5970, 10660, 3200, 12790, 5330, 1570,…
## $ total_price    <dbl> 6070, 5970, 2770, 5970, 10660, 3200, 12790, 5330, 1570,…
## $ model          <chr> "Jekyll Carbon 2", "Trigger Carbon 2", "Beast of the Ea…
## $ category_1     <chr> "Mountain", "Mountain", "Mountain", "Mountain", "Road",…
## $ category_2     <chr> "Over Mountain", "Over Mountain", "Trail", "Over Mounta…
## $ frame_material <chr> "Carbon", "Carbon", "Aluminum", "Carbon", "Carbon", "Ca…
## $ bikeshop_name  <chr> "Ithaca Mountain Climbers", "Ithaca Mountain Climbers",…
## $ city           <chr> "Ithaca", "Ithaca", "Kansas City", "Kansas City", "Loui…
## $ state          <chr> "NY", "NY", "KS", "KS", "KY", "KY", "KY", "KY", "KY", "…

Step 4: Group data by category_2 and summarize revenue

revenue_by_category2 <- bike_orderlines %>%
  group_by(category_2) %>%
  summarise(revenue = sum(total_price, na.rm = TRUE)) %>%
  arrange(desc(revenue))

Step 5: Create a horizontal bar chart

ggplot(revenue_by_category2, aes(x = revenue, y = reorder(category_2, revenue))) +
  geom_bar(stat = "identity", fill = "blue") +
  labs(x = "revenue", y = "category_2") +
  theme_minimal()