Filter Missing Values Example

filtering.R

# dyplyr is used for such cases:
library(dplyr)

# Create a small dataset with missing values:
students <- data.frame(
  name = c("Alice", "Bob", "Charlie", "Diana", "Eve"),
  age = c(20, NA, 22, 19, NA),
  grade = c(85, 92, NA, 78, 88),
  city = c("Boston", "Chicago", NA, "Denver", "Austin")
)

# Display original dataset
print(students)

# Filter rows where specific column is NOT missing
students_with_age <- students %>%
  filter(!is.na(age))

print("\nStudents with age data:")
print(students_with_age)

# Filter rows where multiple columns are NOT missing
students_age_and_grade <- students %>%
  filter(!is.na(age) & !is.na(grade))

print("\nStudents with both age and grade:")
print(students_age_and_grade)

# Digression: Filter rows with NO missing values (complete cases)
complete_data <- students %>%
  filter(complete.cases(.))

print("\nRows with no missing values:")
print(complete_data)