EXERCISE 1
set.seed(42)
# Data
student_data <- data.frame(
student_id = 1:50,
name = paste0("Student", 1:50),
midterm1 = sample(60:100, 50, replace = TRUE),
midterm2 = sample(60:100, 50, replace = TRUE),
final = sample(60:100, 50, replace = TRUE)
)
# Transform data to long format using gather:
student_data_long <- student_data %>% gather(exam_type, score, midterm1:final)
# Print first few rows:
head(student_data_long)
## student_id name exam_type score
## 1 1 Student1 midterm1 96
## 2 2 Student2 midterm1 60
## 3 3 Student3 midterm1 84
## 4 4 Student4 midterm1 69
## 5 5 Student5 midterm1 95
## 6 6 Student6 midterm1 77
EXERCISE 2
set.seed(42)
# Data
student_data2 <- data.frame(
student_id = 1:50,
name_age = c("John_21", "Alice_20", "Bob_22", "Emily_23", "Michael_22"),
exam_scores = c("midterm1_80,midterm2_85,final_75", "midterm1_75,midterm2_78,final_80", "midterm1_82,midterm2_80,final_85", "midterm1_88,midterm2_90,final_92", "midterm1_85,midterm2_86,final_88")
)
# Split variables name_age to 2 separate columns: name and age
student_data2_split <- student_data2 %>%
separate(name_age, c("name", "age")) %>%
# Split variables exam_scores to separate columns for each exam type
separate(exam_scores, c("midterm1", "midterm2", "final"), sep = ",") %>%
separate(midterm1, c("exam_name", "midterm1"), sep = "_") %>%
select(-exam_name) %>%
separate(midterm2, c("exam_name", "midterm2"), sep = "_") %>%
select(-exam_name) %>%
separate(final, c("exam_name", "final"), sep = "_") %>%
select(-exam_name)
# Transform student_data2 to long format
student_data2_long <- student_data2_split %>%
pivot_longer(cols = c(midterm1, midterm2, final), names_to = "exam_name", values_to = "exam_score")
head(student_data2_split)
## student_id name age midterm1 midterm2 final
## 1 1 John 21 80 85 75
## 2 2 Alice 20 75 78 80
## 3 3 Bob 22 82 80 85
## 4 4 Emily 23 88 90 92
## 5 5 Michael 22 85 86 88
## 6 6 John 21 80 85 75
## # A tibble: 6 × 5
## student_id name age exam_name exam_score
## <int> <chr> <chr> <chr> <chr>
## 1 1 John 21 midterm1 80
## 2 1 John 21 midterm2 85
## 3 1 John 21 final 75
## 4 2 Alice 20 midterm1 75
## 5 2 Alice 20 midterm2 78
## 6 2 Alice 20 final 80
EXERCISE 3
set.seed(42)
# Data
student_data3 <- data.frame(
student_id = 1:50,
name_age = c("John_21", "Alice_20", "Bob_22", "Emily_23", "Michael_22"),
exam_scores = c("midterm1_80,midterm2_85,final_75", "midterm1_75,midterm2_78,final_80", "midterm1_82,midterm2_80,final_85", "midterm1_88,midterm2_90,final_92", "midterm1_85,midterm2_86,final_88")
)
# Complete missing combinations for students
student_data_complete <- student_data3 %>%
complete(student_id = full_seq(student_id, period = 1),
fill = list(name_age = "unknown", exam_scores = 0))
head(student_data_complete)
## # A tibble: 6 × 3
## student_id name_age exam_scores
## <dbl> <chr> <chr>
## 1 1 John_21 midterm1_80,midterm2_85,final_75
## 2 2 Alice_20 midterm1_75,midterm2_78,final_80
## 3 3 Bob_22 midterm1_82,midterm2_80,final_85
## 4 4 Emily_23 midterm1_88,midterm2_90,final_92
## 5 5 Michael_22 midterm1_85,midterm2_86,final_88
## 6 6 John_21 midterm1_80,midterm2_85,final_75
EXERCISE 4
set.seed(42)
# Data
student_data4 <- data.frame(
student_id = 1:50,
name_age = c("John_21", "Alice_20", "Bob_22", "Emily_23", "Michael_22"),
exam_scores = c("midterm1_80,midterm2_85,final_75", "midterm1_75,midterm2_78,final_80", "midterm1_82,midterm2_80,final_85", "midterm1_88,midterm2_90,final_92", "midterm1_85,midterm2_86,final_88")
)
# Transform data to wide format
student_data_wide <- student_data4 %>%
unite(student, student_id, name_age, sep = ".") %>%
pivot_wider(names_from = "student", values_from = "exam_scores")
head(student_data_wide)
## # A tibble: 1 × 50
## `1.John_21` `2.Alice_20` `3.Bob_22` `4.Emily_23` `5.Michael_22` `6.John_21`
## <chr> <chr> <chr> <chr> <chr> <chr>
## 1 midterm1_80,m… midterm1_75… midterm1_… midterm1_88… midterm1_85,m… midterm1_8…
## # ℹ 44 more variables: `7.Alice_20` <chr>, `8.Bob_22` <chr>,
## # `9.Emily_23` <chr>, `10.Michael_22` <chr>, `11.John_21` <chr>,
## # `12.Alice_20` <chr>, `13.Bob_22` <chr>, `14.Emily_23` <chr>,
## # `15.Michael_22` <chr>, `16.John_21` <chr>, `17.Alice_20` <chr>,
## # `18.Bob_22` <chr>, `19.Emily_23` <chr>, `20.Michael_22` <chr>,
## # `21.John_21` <chr>, `22.Alice_20` <chr>, `23.Bob_22` <chr>,
## # `24.Emily_23` <chr>, `25.Michael_22` <chr>, `26.John_21` <chr>, …
EXERCISE 5
set.seed(42)
# Data
student_data5 <- data.frame(
student_id = 1:50,
name_age = c("John_21", "Alice_20", "Bob_22", "Emily_23", "Michael_22"),
exam_scores = c("midterm1_80,midterm2_85,final_75", "midterm1_75,midterm2_78,final_80", "midterm1_82,midterm2_80,final_85", "midterm1_88,midterm2_90,final_92", "midterm1_85,midterm2_86,final_88")
)
student_data5_unite <- student_data2 %>%
separate(name_age, c("name", "age")) %>%
# Merge variables name and age to one column called name_age
unite(name_age, name, age, sep = "_")
head(student_data5)
## student_id name_age exam_scores
## 1 1 John_21 midterm1_80,midterm2_85,final_75
## 2 2 Alice_20 midterm1_75,midterm2_78,final_80
## 3 3 Bob_22 midterm1_82,midterm2_80,final_85
## 4 4 Emily_23 midterm1_88,midterm2_90,final_92
## 5 5 Michael_22 midterm1_85,midterm2_86,final_88
## 6 6 John_21 midterm1_80,midterm2_85,final_75