1. Fix typos found in Feature Engineering
Data$model <- gsub("CAAD Disk Ultegra", "CAAD12 Disc Ultegra", Data$model)
Data$model <- gsub("Syapse Carbon Tiagra", "Synapse Carbon Tiagra", Data$model)
Data$model <- gsub("Supersix Evo Hi-Mod Utegra", "Supersix Evo Hi-Mod Ultegra", Data$model)
## Rows: 15,644
## Columns: 13
## $ 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…
## $ 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", "…
2. Which month has the highest bike sales?
## # A tibble: 12 × 2
## Month Sales
## <ord> <chr>
## 1 Jan $4,089,460
## 2 Feb $5,343,295
## 3 Mar $7,282,280
## 4 Apr $8,386,170
## 5 May $7,935,055
## 6 Jun $7,813,105
## 7 Jul $7,602,005
## 8 Aug $5,346,125
## 9 Sep $5,556,055
## 10 Oct $4,394,300
## 11 Nov $4,169,755
## 12 Dec $3,114,725
3. What is the median orderline sales value by Bike Attribute?
## # A tibble: 2 × 2
## Black Median_Orderline
## <lgl> <chr>
## 1 FALSE $2,880
## 2 TRUE $12,250
## # A tibble: 2 × 2
## Ultegra Median_Orderline
## <lgl> <chr>
## 1 FALSE $3,200
## 2 TRUE $3,200
## # A tibble: 2 × 2
## Disc Median_Orderline
## <lgl> <chr>
## 1 FALSE $3,200
## 2 TRUE $2,660
## `summarise()` has grouped output by 'category_1', 'category_2'. You can
## override using the `.groups` argument.
## # A tibble: 21 × 6
## category_1 category_2 model_base mean_price min_price max_price
## <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Mountain Cross Country Race Scalpel-Si Race $9,060 $9,060 $9,060
## 2 Mountain Cross Country Race Scalpel-Si Hi-M… $7,460 $7,460 $7,460
## 3 Mountain Sport Catalyst $546 $415 $705
## 4 Road Elite Road Supersix $5,491 $1,840 $12,790
## 5 Mountain Cross Country Race Scalpel-Si Carb… $5,327 $4,260 $6,390
## 6 Mountain Over Mountain Jekyll $5,275 $3,200 $7,990
## 7 Mountain Over Mountain Trigger $5,275 $3,200 $8,200
## 8 Mountain Cross Country Race F-Si $5,070 $1,840 $11,190
## 9 Mountain Trail Habit $5,052 $1,950 $12,250
## 10 Mountain Cross Country Race Scalpel 29 $4,795 $3,200 $6,390
## # ℹ 11 more rows