library(tidyr)
# Data
student_data1 <- 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_long1 <- gather(student_data1, exam, score, -student_id, -name)
# Print first few rows:
head(student_data_long1)
## student_id name exam score
## 1 1 Student1 midterm1 76
## 2 2 Student2 midterm1 94
## 3 3 Student3 midterm1 95
## 4 4 Student4 midterm1 83
## 5 5 Student5 midterm1 65
## 6 6 Student6 midterm1 90
library(tidyr)
# 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
seperated<-separate(student_data2, name_age, c('name', 'age'), sep = '_')
head(seperated)
## 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
# Split variables exam_scores to separate columns for each exam type
seperated_exams<-separate(student_data2, exam_scores, c("midterm1", "midterm2", "final"), sep = ",")
head(seperated_exams)
## student_id name_age midterm1 midterm2 final
## 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
# Transform student_data2 to long format: data is already in long format
library(tidyr)
set.seed(1)
# Data
student_data <- 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
pom<- separate(student_data, name_age, c('name','age'), '_')
pom2<- separate_rows(pom, exam_scores, sep = ',')
pom3<- separate(pom2, exam_scores, c('exam', 'score'), '_')
complete(pom3, student_id, name, age, exam, score)
## # A tibble: 27,000 × 5
## student_id name age exam score
## <int> <chr> <chr> <chr> <chr>
## 1 1 Alice 20 final 75
## 2 1 Alice 20 final 78
## 3 1 Alice 20 final 80
## 4 1 Alice 20 final 82
## 5 1 Alice 20 final 85
## 6 1 Alice 20 final 86
## 7 1 Alice 20 final 88
## 8 1 Alice 20 final 90
## 9 1 Alice 20 final 92
## 10 1 Alice 20 midterm1 75
## # ℹ 26,990 more rows
library(tidyr)
# Data
student_data <- 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<-separate(student_data, exam_scores, into = c("midterm1", "midterm2", "final"), sep = ",")
student_data_wide<-separate(student_data_wide, name_age, into = c('name', 'age'), sep = '_')
student_data_wide <- spread(student_data_wide, key = midterm1, value = midterm1)
head(student_data_wide)
## student_id name age midterm2 final midterm1_75 midterm1_80
## 1 1 John 21 midterm2_85 final_75 <NA> midterm1_80
## 2 2 Alice 20 midterm2_78 final_80 midterm1_75 <NA>
## 3 3 Bob 22 midterm2_80 final_85 <NA> <NA>
## 4 4 Emily 23 midterm2_90 final_92 <NA> <NA>
## 5 5 Michael 22 midterm2_86 final_88 <NA> <NA>
## 6 6 John 21 midterm2_85 final_75 <NA> midterm1_80
## midterm1_82 midterm1_85 midterm1_88
## 1 <NA> <NA> <NA>
## 2 <NA> <NA> <NA>
## 3 midterm1_82 <NA> <NA>
## 4 <NA> <NA> midterm1_88
## 5 <NA> midterm1_85 <NA>
## 6 <NA> <NA> <NA>
library(tidyr)
# Data
student_data <- 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")
)
# Merge variables name and age to one column called name_age
merge<-unite(seperated, col = "name_age", c("name", "age"), sep = "_" )
head(merge)
## 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