library(testthat)
source("user_code.R")

test_that("data frame has at least two columns with missing values", {
  set.seed(42)
  data <- data.frame(
    id = 1:10,
    age = c(NA, 30, NA, NA, NA, NA, NA, 32, 29, NA),
    income = c(NA, 60000, NA, NA, NA, NA, NA, 62000, 58000, NA)
  )
  expect_true(any(is.na(data$age)), "Column 'age' should contain missing values.")
  expect_true(any(is.na(data$income)), "Column 'income' should contain missing values.")
})

test_that("total number of missing values is correctly counted and returned", {
  result <- simulate_and_clean_data()
  expect_true(is.list(result), "Function should return a list.")
  expect_true("missing_count" %in% names(result), "List should contain 'missing_count'.")
  expect_equal(result$missing_count, 14, info = "Should return total number of missing values, which is 14.")
})

test_that("all rows with missing values are removed and cleaned data is returned", {
  result <- simulate_and_clean_data()
  expect_true("cleaned_data" %in% names(result), "List should contain 'cleaned_data'.")
  cleaned <- result$cleaned_data
  expect_true(is.data.frame(cleaned), "cleaned_data should be a data frame.")
  expect_equal(nrow(cleaned), 3, info = "Cleaned data should have 3 rows.")
  expect_equal(ncol(cleaned), 3, info = "Cleaned data should have 3 columns.")
  expect_equal(cleaned$id, c(2, 8, 9), info = "Cleaned data should have correct 'id's.")
  expect_equal(cleaned$age, c(30, 32, 29), info = "Cleaned data should have correct 'age's.")
  expect_equal(cleaned$income, c(60000, 62000, 58000), info = "Cleaned data should have correct 'income's.")
  expect_equal(sum(is.na(cleaned)), 0, info = "There should be no missing values in cleaned_data.")
})

test_main.R

This practical course introduces learners to essential data cleaning and wrangling techniques in R. Through hands-on exercises, students will learn how to handle missing data, transform and recode variables, filter and select relevant data, and prepare datasets for analysis. The course emphasizes using popular R packages such as dplyr and tidyr to streamline and automate data preparation workflows, equipping learners with the foundational skills needed for effective data analysis.

Master the core techniques for cleaning and wrangling data in R using dplyr and tidyr. Each concept is introduced in a theory chapter, followed by a practical challenge.

Challenge: Handling Missing Data

Ratkaisu