Data Wrangling
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
set.seed(2313213)
library(tidyr)
# 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<-gather(student_data, key="exam",value="points" , 3:5)
# Print first few rows:
head(student_data_long)## student_id name exam points
## 1 1 Student1 midterm1 100
## 2 2 Student2 midterm1 93
## 3 3 Student3 midterm1 90
## 4 4 Student4 midterm1 94
## 5 5 Student5 midterm1 66
## 6 6 Student6 midterm1 76# 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 long format
# This data frame is already in long format:)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
student_data2<-separate(student_data2,2,c("name","age") ,"_")
head(student_data2)## 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
student_data2<-separate(student_data2,4,c("midterm1","midterm2","final"),",")
head(student_data2)## 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
student_data2 <- gather(student_data2, key = "exam", value = "points",4:6)
student_data2 <- separate(student_data2,5,c("exam","points"),"_")
head(student_data2)## student_id name age exam points
## 1 1 John 21 midterm1 80
## 2 2 Alice 20 midterm1 75
## 3 3 Bob 22 midterm1 82
## 4 4 Emily 23 midterm1 88
## 5 5 Michael 22 midterm1 85
## 6 6 John 21 midterm1 80library(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")
)
# Complete missing combinations for students
student_data <- separate(student_data,3,c("midterm1", "midterm2", "final"), ",")
head(student_data)## 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## # A tibble: 6 × 5
## midterm1 midterm2 final student_id name_age
## <chr> <chr> <chr> <int> <chr>
## 1 midterm1_75 midterm2_78 final_75 NA <NA>
## 2 midterm1_75 midterm2_78 final_80 2 Alice_20
## 3 midterm1_75 midterm2_78 final_80 7 Alice_20
## 4 midterm1_75 midterm2_78 final_80 12 Alice_20
## 5 midterm1_75 midterm2_78 final_80 17 Alice_20
## 6 midterm1_75 midterm2_78 final_80 22 Alice_20# Transform data to wide format
student_data2<-spread(student_data2,key="exam",value="points")
head(student_data2)## student_id name age final midterm1 midterm2
## 1 1 John 21 75 80 85
## 2 2 Alice 20 80 75 78
## 3 3 Bob 22 85 82 80
## 4 4 Emily 23 92 88 90
## 5 5 Michael 22 88 85 86
## 6 6 John 21 75 80 85## student_id name age final midterm1 midterm2
## 1 1 John 21 75 80 85
## 2 2 Alice 20 80 75 78
## 3 3 Bob 22 85 82 80
## 4 4 Emily 23 92 88 90
## 5 5 Michael 22 88 85 86
## 6 6 John 21 75 80 85## student_id name_age final midterm1 midterm2
## 1 1 John_21 75 80 85
## 2 2 Alice_20 80 75 78
## 3 3 Bob_22 85 82 80
## 4 4 Emily_23 92 88 90
## 5 5 Michael_22 88 85 86
## 6 6 John_21 75 80 85