in-class exercise

install.packages(c("readxl", "dplyr", "ggplot2"))

## Installing packages into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)

library(readxl)
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)

bikeorderline <- read_excel("bike_orderlines.xlsx")

revenue_column_name <- "price"
bikeorderline[[revenue_column_name]] <- as.numeric(bikeorderline[[revenue_column_name]])

top_bikeshops <- bikeorderline %>%
  group_by(bikeshop_name) %>%
  summarise(revenue = sum(.data[[revenue_column_name]])) %>%
  arrange(desc(revenue)) %>%
  head(10)


other_bikeshops <- bikeorderline %>%
  group_by(bikeshop_name) %>%
  summarise(revenue = sum(.data[[revenue_column_name]])) %>%
  anti_join(top_bikeshops, by = "bikeshop_name") %>%
  summarise(bikeshop_name = "Other Bikeshops", revenue = sum(revenue))

# Combine Top 10 and "Other Bikeshops"
final_data <- rbind(top_bikeshops, other_bikeshops)

# Plot the Results
ggplot(final_data, aes(x = reorder(bikeshop_name, -revenue), y = revenue)) +
  geom_bar(stat = "identity", fill = "skyblue") +
  labs(title = "Top 10 Bikeshops by Revenue",
       x = "Bikeshop Name",
       y = "Revenue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))