hw5

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(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.4
## ✔ ggplot2   3.4.2     ✔ stringr   1.5.0
## ✔ lubridate 1.9.2     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.0

## ── 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

bike_data <- readRDS("bike_orderlines (1).rds")

category_1_unique <- bike_data %>%
  group_by(category_1) %>%
  summarise() %>%
  ungroup()

category_2_unique <- bike_data %>%
  group_by(category_2) %>%
  summarise() %>%
  ungroup()

frame_material_unique <- bike_data %>%
  group_by(frame_material) %>%
  summarise() %>%
  ungroup()

cat("Unique values in category_1:\n")

## Unique values in category_1:

print(category_1_unique)

## # A tibble: 2 × 1
##   category_1
##   <chr>     
## 1 Mountain  
## 2 Road

cat("\nUnique values in category_2:\n")

## 
## Unique values in category_2:

print(category_2_unique)

## # A tibble: 9 × 1
##   category_2        
##   <chr>             
## 1 Cross Country Race
## 2 Cyclocross        
## 3 Elite Road        
## 4 Endurance Road    
## 5 Fat Bike          
## 6 Over Mountain     
## 7 Sport             
## 8 Trail             
## 9 Triathalon

cat("\nUnique values in frame_material:\n")

## 
## Unique values in frame_material:

print(frame_material_unique)

## # A tibble: 2 × 1
##   frame_material
##   <chr>         
## 1 Aluminum      
## 2 Carbon

primary_sales <- bike_data %>%
  group_by(category_1) %>%
  summarise(Sales = sum(total_price, na.rm = TRUE), .groups = "drop") %>%
  rename("Primary Category" = category_1) %>%
  arrange(desc(Sales))

cat("\nSales by Primary Category:\n")

## 
## Sales by Primary Category:

print(primary_sales)

## # A tibble: 2 × 2
##   `Primary Category`    Sales
##   <chr>                 <dbl>
## 1 Mountain           39154735
## 2 Road               31877595

secondary_sales <- bike_data %>%
  group_by(category_2) %>%
  summarise(Sales = sum(total_price, na.rm = TRUE), .groups = "drop") %>%
  rename("Secondary Category" = category_2) %>%
  arrange(desc(Sales))

cat("\nSales by Secondary Category:\n")

## 
## Sales by Secondary Category:

print(secondary_sales)

## # A tibble: 9 × 2
##   `Secondary Category`    Sales
##   <chr>                   <dbl>
## 1 Cross Country Race   19224630
## 2 Elite Road           15334665
## 3 Endurance Road       10381060
## 4 Trail                 9373460
## 5 Over Mountain         7571270
## 6 Triathalon            4053750
## 7 Cyclocross            2108120
## 8 Sport                 1932755
## 9 Fat Bike              1052620

frame_material_sales <- bike_data %>%
  group_by(frame_material) %>%
  summarise(Sales = sum(total_price, na.rm = TRUE), .groups = "drop") %>%
  rename("Frame Material" = frame_material) %>%
  arrange(desc(Sales))

cat("\nSales by Frame Material:\n")

## 
## Sales by Frame Material:

print(frame_material_sales)

## # A tibble: 2 × 2
##   `Frame Material`    Sales
##   <chr>               <dbl>
## 1 Carbon           52940540
## 2 Aluminum         18091790

category_frame_check <- bike_data %>%
  group_by(category_1, category_2, frame_material) %>%
  summarise(Sales = sum(total_price, na.rm = TRUE), .groups = "drop") %>%
  pivot_wider(names_from = frame_material, values_from = Sales, values_fill = 0)
category_frame_check <- category_frame_check %>%
  rename("Primary Category" = category_1, "Secondary Category" = category_2)

cat("\nSales by Primary and Secondary Category with Frame Materials:\n")

## 
## Sales by Primary and Secondary Category with Frame Materials:

print(category_frame_check)

## # A tibble: 9 × 4
##   `Primary Category` `Secondary Category` Aluminum   Carbon
##   <chr>              <chr>                   <dbl>    <dbl>
## 1 Mountain           Cross Country Race    3318560 15906070
## 2 Mountain           Fat Bike              1052620        0
## 3 Mountain           Over Mountain               0  7571270
## 4 Mountain           Sport                 1932755        0
## 5 Mountain           Trail                 4537610  4835850
## 6 Road               Cyclocross                  0  2108120
## 7 Road               Elite Road            5637795  9696870
## 8 Road               Endurance Road        1612450  8768610
## 9 Road               Triathalon                  0  4053750