Complete Cases in R (3 Programming Examples)

data <- data.frame(x1 = c(7, 2, 1, NA, 9), # Some example data
                   x2 = c(1, 3, 1, 9, NA),
                   x3 = c(NA, 8, 8, NA, 5))
data # This is how our example data looks like

complete.cases(data)
# [1] FALSE  TRUE  TRUE FALSE FALSE

data[complete.cases(data), ] # Keep only the complete rows
data_complete <- data[complete.cases(data), ] # Store the complete cases subset in a new data frame

set.seed(10101) # Set seed in order to create a reproducible example
vec <- round(runif(20, 0, 10)) # Create example vector
vec[rbinom(20, 1, 0.2) == 1] <- NA # Insert some NA values to the vector
 
complete.cases(vec) # The R programming language uses for vectors the same procedure as for data frames
# [1] FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
# [2] TRUE  TRUE FALSE  TRUE  TRUE FALSE  TRUE FALSE FALSE  TRUE
 
# Delete missing values and store the complete vector in the new object
vec_completevec_complete <- vec[complete.cases(vec)]

# Load and inspect data
data(airquality) # Load the data set airquality
dim(airquality) # The data has 153 rows and 6 columns
head(airquality) # Head of data; Missing values are, for instance, in column 1 & 2 in row 5
 
# Check the whole data frame for missing values
complete.cases(airquality) # TRUE indicates a complete row; FALSE indicates a row with at least
                           # one incomplete column
sum(complete.cases(airquality)) # We have 111 complete rows
airquality_complete <- airquality[complete.cases(airquality), ] # Create new data without missing values
 
# Find incomplete cases in a column
complete.cases(airquality$Ozone) # By adding $Ozone behind airquality,
                                 # we identify observed values in the column Ozone
sum(complete.cases(airquality$Ozone)) # We have 116 observations
Ozone_complete <- airquality$Ozone[complete.cases(airquality$Ozone)] # Exclude missing data
                                                                     # from our column vector

set.seed(34756) # Set seed
 
data_header <- data.frame(Household_ID = runif(100), # Some dummy data
                          Sex = runif(100),
                          Age = runif(100),
                          Nationality = runif(100),
                          Year = runif(100),
                          Health = runif(100),
                          CoB = runif(100),
                          Income = runif(100),
                          Household_Size = runif(100),
                          Holidays = runif(100),
                          Marital_Status = runif(100),
                          Expenditure = runif(100))
 
data_header$Sex[rbinom(100, 1, 0.1) == 1] <- NA # Insert NA's
data_header$Age[rbinom(100, 1, 0.15) == 1] <- NA
data_header$Nationality[rbinom(100, 1, 0.1) == 1] <- NA
data_header$Year[1:7] <- NA
data_header$Health[rbinom(100, 1, 0.25) == 1] <- NA
data_header$Income[rbinom(100, 1, 0.4) == 1] <- NA
data_header$Marital_Status[rbinom(100, 1, 0.05) == 1] <- NA
data_header$Expenditure[rbinom(100, 1, 0.25) == 1] <- NA
 
data_logical <- as.data.frame(is.na(data_header) == FALSE) # Check for missing data
data_logical