lab3

# 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")
)

# Split variables name_age to 2 separate columns: name and age

student_data_separated <- separate(
  student_data,
  col = "name_age",
  into = c ("name" , "age"),
  sep = "_",
  remove = TRUE,
  convert = FALSE,
  extra = "warn",
  fill = "warn",
)

# Split variables exam_scores to separate columns for each exam type

student_data_separated <- separate(
  student_data_separated,
  col = "exam1",
  into = c ("exam1", "score1"),
  sep = "_",
  remove = TRUE,
  convert = FALSE,
  extra = "warn",
  fill = "warn",
)

student_data_separated <- separate(
  student_data_separated,
  col = "exam2",
  into = c ("exam2", "score2"),
  sep = "_",
  remove = TRUE,
  convert = FALSE,
  extra = "warn",
  fill = "warn",
)

student_data_separated <- separate(
  student_data_separated,
  col = "exam3",
  into = c ("exam3", "score3"),
  sep = "_",
  remove = TRUE,
  convert = FALSE,
  extra = "warn",
  fill = "warn",
)

# Complete missing combinations for students

student_data_separated <- complete (
  student_data_separated,
 name,
 age,
  fill = list(),
  explicit = TRUE,
  )

# Transform data to wide format

#student_data_separated_spread <- spread(
  #student_data_separated,
  #key,
  ##value,
  #fill = NA,
  #convert = FALSE,
  #drop = TRUE,
  #sep = NULL,
  #)

# Merge variables name and age to one column called name_age


student_data_separated <- unite(
  student_data_separated,
  col = "name_age",
  name,
  age,
  sep = "_",
  remove = TRUE,
  na.rm = FALSE,
  )

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.