hw_3

# Sample data frame
bike_orderline_tbl <- data.frame(
  category_1 = c("A", "A", "B", "B", "C"),
  category_2 = c("X", "Y", "X", "Y", "X"),
  frame_material = c("Aluminum", "Steel", "Aluminum", "Steel", "Aluminum"),
  Sales = c(100, 150, 120, 200, 80)
)


# 1. Use 'bike_orderline_tbl'.

# 2. Group and summarize the data, calling the new column 'Sales'.
# You need to specify the grouping variables and the summarization function.
# In this example, we'll group by 'category_1', 'category_2', and 'frame_material',
# and calculate the total sales for each group.
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

result <- bike_orderline_tbl %>%
  group_by(`category_1`, `category_2`, `frame_material`) %>%
  summarise(Sales = sum(Sales))

## `summarise()` has grouped output by 'category_1', 'category_2'. You can
## override using the `.groups` argument.

# 3. Format the 'Sales' column as 'dollars()'.
result$Sales <- scales::dollar(result$Sales)

# 4. Rename the columns as specified.
result <- result %>%
  rename(`Prime category` = `category_1`,
         `Secondary category` = `category_2`,
         `Frame Material` = `frame_material`)

# View the result
print(result)

## # A tibble: 5 × 4
## # Groups:   Prime category, Secondary category [5]
##   `Prime category` `Secondary category` `Frame Material` Sales
##   <chr>            <chr>                <chr>            <chr>
## 1 A                X                    Aluminum         $100 
## 2 A                Y                    Steel            $150 
## 3 B                X                    Aluminum         $120 
## 4 B                Y                    Steel            $200 
## 5 C                X                    Aluminum         $80