Clean missing values (NA) in R in these easy steps

clean_na_with_R.r

# install tidyverse
install.packages("tidyverse")
library(tidyverse)

# step 1 -- review example dataset 'msleep' in tidyverse package
glimpse(msleep)
summary(msleep)

# step 2.1 -- remove all rows with missing values
clean_msleep <- drop_na(msleep)

# step 2.2 -- impute NA with mean or median values
# mean imputation
mean_sleep_rem <- mean(msleep$sleep_rem, na.rm=TRUE)
msleep$sleep_rem <- replace_na(msleep$sleep_rem, mean_sleep_rem)

# median imputation
median_sleep_rem <- median(msleep$sleep_rem, na.rm=TRUE)
msleep$sleep_rem <- replace_na(msleep$sleep_rem, median_sleep_rem)

# export clean dataframe to our working directory
write.csv(clean_msleep, "clean_msleep.csv")

# finished !!