
library(testthat)

source("user_code.R")
test_that("removes all duplicates except first occurrence", {
  df_test <- data.frame(
    id = c(1, 2, 2, 3, 4, 4, 4, 5),
    name = c("Alice", "Bob", "Bob", "Charlie", "David", "David", "David", "Eve"),
    score = c(90, 85, 85, 88, 92, 92, 92, 95),
    stringsAsFactors = FALSE
  )
  result <- detect_and_remove_duplicates(df_test)
  expect_true(is.data.frame(result), "Output should be a data frame.")
  expect_equal(nrow(result), 5, info = "Should have 5 unique rows.")
  expect_equal(result$id, c(1,2,3,4,5), info = "Order of first occurrences should be preserved.")
  expect_equal(result$name, c("Alice","Bob","Charlie","David","Eve"), info = "Names should be correct after removing duplicates.")
  expect_equal(result$score, c(90,85,88,92,95), info = "Scores should be correct after removing duplicates.")
})

test_that("returns same data frame when no duplicates present", {
  df_unique <- data.frame(
    id = 1:4,
    name = c("A","B","C","D"),
    score = c(10,20,30,40),
    stringsAsFactors = FALSE
  )
  result <- detect_and_remove_duplicates(df_unique)
  expect_equal(result, df_unique, info = "Data frame with no duplicates should be unchanged.")
})

test_that("returns single row when all rows are duplicates", {
  df_dupes <- data.frame(
    id = c(7,7,7,7),
    name = c("Z","Z","Z","Z"),
    score = c(55,55,55,55),
    stringsAsFactors = FALSE
  )
  result <- detect_and_remove_duplicates(df_dupes)
  expect_true(is.data.frame(result), "Output should be a data frame.")
  expect_equal(nrow(result), 1, info = "Should keep only one row when all are duplicates.")
  expect_equal(result$id, 7)
  expect_equal(result$name, "Z")
  expect_equal(result$score, 55)
})

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: Detecting and Removing Duplicates

Solution