read in the data:
piaac<-read.csv("http://www.ut.ee/~iseppo/piaacexam.csv")
## # A tibble: 18 x 3
## # Groups: gender [2]
## gender studyarea averageWage
## <fct> <fct> <dbl>
## 1 Female Agriculture and veterinary 702.
## 2 Female Engineering, manufacturing and construction 725.
## 3 Female General programmes 576.
## 4 Female Health and welfare 1041.
## 5 Female Humanities, languages and arts 813.
## 6 Female Science, mathematics and computing 851.
## 7 Female Services 862.
## 8 Female Social sciences, business and law 936.
## 9 Female Teacher training and education science 781.
## 10 Male Agriculture and veterinary 1032.
## 11 Male Engineering, manufacturing and construction 1336.
## 12 Male General programmes 869.
## 13 Male Health and welfare 1468.
## 14 Male Humanities, languages and arts 936.
## 15 Male Science, mathematics and computing 1458.
## 16 Male Services 1185.
## 17 Male Social sciences, business and law 1526.
## 18 Male Teacher training and education science 810.
## # A tibble: 9 x 3
## studyarea Female Male
## <fct> <dbl> <dbl>
## 1 Agriculture and veterinary 702. 1032.
## 2 Engineering, manufacturing and construction 725. 1336.
## 3 General programmes 576. 869.
## 4 Health and welfare 1041. 1468.
## 5 Humanities, languages and arts 813. 936.
## 6 Science, mathematics and computing 851. 1458.
## 7 Services 862. 1185.
## 8 Social sciences, business and law 936. 1526.
## 9 Teacher training and education science 781. 810.
Think from which variable are the new variable names coming from and from which are the values coming from and it should be doable.