exam <- read.csv("csv_exam.csv")
dplyr::glimpse(exam)## Observations: 20
## Variables: 5
## $ id <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,...
## $ class <int> 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, ...
## $ math <int> 50, 60, 45, 30, 25, 50, 80, 90, 20, 50, 65, 45, 46, 48...
## $ english <int> 98, 97, 86, 98, 80, 89, 90, 78, 98, 98, 65, 85, 98, 87...
## $ science <int> 50, 60, 78, 58, 65, 98, 45, 25, 15, 45, 65, 32, 65, 12...exam %>%
mutate(total = math + english + science) %>%
head## id class math english science total
## 1 1 1 50 98 50 198
## 2 2 1 60 97 60 217
## 3 3 1 45 86 78 209
## 4 4 1 30 98 58 186
## 5 5 2 25 80 65 170
## 6 6 2 50 89 98 237exam %>%
mutate(tatal = math + english + science, mean = (math + english + science)/3) %>%
head## id class math english science tatal mean
## 1 1 1 50 98 50 198 66.00000
## 2 2 1 60 97 60 217 72.33333
## 3 3 1 45 86 78 209 69.66667
## 4 4 1 30 98 58 186 62.00000
## 5 5 2 25 80 65 170 56.66667
## 6 6 2 50 89 98 237 79.00000exam %>%
mutate(test = ifelse(science >=60, "pass", "fail")) %>%
head## id class math english science test
## 1 1 1 50 98 50 fail
## 2 2 1 60 97 60 pass
## 3 3 1 45 86 78 pass
## 4 4 1 30 98 58 fail
## 5 5 2 25 80 65 pass
## 6 6 2 50 89 98 passexam %>%
mutate(total = math + english + science) %>%
arrange(desc(total)) %>%
head## id class math english science total
## 1 18 5 80 78 90 248
## 2 19 5 89 68 87 244
## 3 6 2 50 89 98 237
## 4 17 5 65 68 98 231
## 5 16 4 58 98 65 221
## 6 20 5 78 83 58 219mpg 데이터는 연비를 나타내는 변수가 hwy(고속도로 연비), cty(도시 연비) 두 종류로 분리되어 있습니다. 두 변수를 각각 활용하는 대신 하나의 통합연비 변수를 만들어 분석하려고 합니다.
mpg_total <- mpg %>% mutate(total = cty + hwy)
head(mpg_total)## # A tibble: 6 x 12
## manufacturer model displ year cyl trans drv cty hwy fl
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr>
## 1 audi a4 1.8 1999 4 auto(l5) f 18 29 p
## 2 audi a4 1.8 1999 4 manual(m5) f 21 29 p
## 3 audi a4 2.0 2008 4 manual(m6) f 20 31 p
## 4 audi a4 2.0 2008 4 auto(av) f 21 30 p
## 5 audi a4 2.8 1999 6 auto(l5) f 16 26 p
## 6 audi a4 2.8 1999 6 manual(m5) f 18 26 p
## # ... with 2 more variables: class <chr>, total <int>-Q2. 앞에서 만든 ‘합산연비 변수’ 를 2로 나눠 ‘평균연비 변수’ 를 추가하세요.
mpg_total <- mpg %>% mutate(total = cty + hwy, mean = total/2)
head(mpg_total)## # A tibble: 6 x 13
## manufacturer model displ year cyl trans drv cty hwy fl
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr>
## 1 audi a4 1.8 1999 4 auto(l5) f 18 29 p
## 2 audi a4 1.8 1999 4 manual(m5) f 21 29 p
## 3 audi a4 2.0 2008 4 manual(m6) f 20 31 p
## 4 audi a4 2.0 2008 4 auto(av) f 21 30 p
## 5 audi a4 2.8 1999 6 auto(l5) f 16 26 p
## 6 audi a4 2.8 1999 6 manual(m5) f 18 26 p
## # ... with 3 more variables: class <chr>, total <int>, mean <dbl>-Q3. ’평균연비변수’가 가장 높은 자동차 3종의 데이터를 출력하세요.
mpg_total %>% arrange(desc(mean)) %>% head(3)## # A tibble: 3 x 13
## manufacturer model displ year cyl trans drv cty hwy
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int>
## 1 volkswagen new beetle 1.9 1999 4 manual(m5) f 35 44
## 2 volkswagen jetta 1.9 1999 4 manual(m5) f 33 44
## 3 volkswagen new beetle 1.9 1999 4 auto(l4) f 29 41
## # ... with 4 more variables: fl <chr>, class <chr>, total <int>,
## # mean <dbl>-Q4. 1~3번 문제를 해결할 수 있는 하나로 연결된 dplyr 구문을 만들어 출력하세요. 데이터는 복사본 대신 mpg 원본을 이용하세요.
mpg %>% mutate(total = cty + hwy, mean = total/2) %>%
arrange(desc(mean)) %>%
head(3)## # A tibble: 3 x 13
## manufacturer model displ year cyl trans drv cty hwy
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int>
## 1 volkswagen new beetle 1.9 1999 4 manual(m5) f 35 44
## 2 volkswagen jetta 1.9 1999 4 manual(m5) f 33 44
## 3 volkswagen new beetle 1.9 1999 4 auto(l4) f 29 41
## # ... with 4 more variables: fl <chr>, class <chr>, total <int>,
## # mean <dbl>