Import data
# excel file
data <- read_excel("../00_data/Salaries.xlsx")
data
## # A tibble: 397 × 6
## rank discipline yrs.since.phd yrs.service sex salary
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 Prof B 19 18 Male 139750
## 2 Prof B 20 16 Male 173200
## 3 AsstProf B 4 3 Male 79750
## 4 Prof B 45 39 Male 115000
## 5 Prof B 40 41 Male 141500
## 6 AssocProf B 6 6 Male 97000
## 7 Prof B 30 23 Male 175000
## 8 Prof B 45 45 Male 147765
## 9 Prof B 21 20 Male 119250
## 10 Prof B 18 18 Female 129000
## # ℹ 387 more rows
Filter
filter(data, rank == "Prof")
## # A tibble: 266 × 6
## rank discipline yrs.since.phd yrs.service sex salary
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 Prof B 19 18 Male 139750
## 2 Prof B 20 16 Male 173200
## 3 Prof B 45 39 Male 115000
## 4 Prof B 40 41 Male 141500
## 5 Prof B 30 23 Male 175000
## 6 Prof B 45 45 Male 147765
## 7 Prof B 21 20 Male 119250
## 8 Prof B 18 18 Female 129000
## 9 Prof B 20 18 Male 104800
## 10 Prof B 12 3 Male 117150
## # ℹ 256 more rows
Arrange
arrange(data,desc(yrs.since.phd))
## # A tibble: 397 × 6
## rank discipline yrs.since.phd yrs.service sex salary
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 Prof A 56 57 Male 76840
## 2 Prof B 56 49 Male 186960
## 3 Prof A 54 49 Male 78162
## 4 Prof A 52 48 Male 107200
## 5 Prof A 51 51 Male 57800
## 6 AssocProf A 49 49 Male 81800
## 7 Prof A 49 43 Male 72300
## 8 Prof B 49 60 Male 192253
## 9 Prof A 49 40 Male 88709
## 10 AssocProf B 48 53 Male 90000
## # ℹ 387 more rows
Select columns
select(data, rank, salary, sex)
## # A tibble: 397 × 3
## rank salary sex
## <chr> <dbl> <chr>
## 1 Prof 139750 Male
## 2 Prof 173200 Male
## 3 AsstProf 79750 Male
## 4 Prof 115000 Male
## 5 Prof 141500 Male
## 6 AssocProf 97000 Male
## 7 Prof 175000 Male
## 8 Prof 147765 Male
## 9 Prof 119250 Male
## 10 Prof 129000 Female
## # ℹ 387 more rows
Add columns
Summarize by groups