
library(testthat)

source("user_code.R")
test_that("Ages less than 18 are set to 18", {
  test_df <- data.frame(employee_id = c("A1", "A2"), name = c("X", "Y"), age = c(15, 18), email = c("x@a.com", "y@a.com"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_equal(res$age[1], 18, info = "Age below 18 should be set to 18")
  expect_equal(res$age[2], 18, info = "Age at lower bound should remain 18")
})

test_that("Ages greater than 65 are set to 65", {
  test_df <- data.frame(employee_id = c("A1", "A2"), name = c("X", "Y"), age = c(70, 65), email = c("x@a.com", "y@a.com"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_equal(res$age[1], 65, info = "Age above 65 should be set to 65")
  expect_equal(res$age[2], 65, info = "Age at upper bound should remain 65")
})

test_that("All employee_id values are unique after correction", {
  test_df <- data.frame(employee_id = c("A1", "A2", "A2", "A3"), name = c("X", "Y", "Z", "W"), age = c(25, 30, 40, 50), email = c("x@a.com", "y@a.com", "z@a.com", "w@a.com"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_equal(length(unique(res$employee_id)), nrow(res), info = "All employee_id values should be unique after correction")
})

test_that("Duplicate employee_id values are modified by appending a suffix", {
  test_df <- data.frame(employee_id = c("A1", "A2", "A2", "A3"), name = c("X", "Y", "Z", "W"), age = c(25, 30, 40, 50), email = c("x@a.com", "y@a.com", "z@a.com", "w@a.com"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_true(any(grepl("A2_", res$employee_id)), info = "Duplicate employee_id should be modified with suffix")
})

test_that("Email values without both '@' and '.' are set to NA", {
  test_df <- data.frame(employee_id = c("A1", "A2", "A3"), name = c("X", "Y", "Z"), age = c(25, 30, 40), email = c("x@a.com", "yexample.com", "z@bcom"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_true(is.na(res$email[2]), info = "Email without '@' should be NA")
  expect_true(is.na(res$email[3]), info = "Email without '.' should be NA")
})

test_that("Valid email formats are preserved", {
  test_df <- data.frame(employee_id = c("A1", "A2"), name = c("X", "Y"), age = c(25, 30), email = c("x@a.com", "y.b@c.org"), stringsAsFactors = FALSE)
  res <- validate_and_correct_employees(test_df)
  expect_equal(res$email, test_df$email, info = "Valid emails should not be modified")
})

test_main.R

Master the essential skills for ensuring data quality in R. Learn to detect and handle missing, duplicated, and inconsistent data, identify outliers, apply data validation rules, and build robust data cleaning pipelines. This course combines engaging theory with hands-on challenges to prepare you for real-world data cleaning tasks.

Explore the foundations of data cleaning and quality assurance in R. Each chapter introduces a core concept, followed by a hands-on challenge to reinforce your learning.

Challenge: Apply Validation Rules to Employee Records

Solution

Challenge: Apply Validation Rules to Employee Records

Solution