
library(testthat)

source("user_code.R")
test_that("returns data frame with correct number of groups", {
  df <- data.frame(category = c("A", "A", "B", "B", "B", "C"), value = c(10, 15, 10, 20, 30, 40))
  res <- aggregate_multiple(df, "category", "value")
  expect_true(is.data.frame(res))
  expect_equal(nrow(res), length(unique(df$category)),
               info = "Should return one row per unique group")
})

test_that("mean column contains correct means", {
  df <- data.frame(category = c("A", "A", "B", "B", "B", "C"), value = c(10, 15, 10, 20, 30, 40))
  res <- aggregate_multiple(df, "category", "value")
  expected_means <- c(A = mean(c(10, 15)), B = mean(c(10, 20, 30)), C = 40)
  rownames(expected_means) <- NULL
  expect_equal(res$Mean[match(names(expected_means), res$Group)], as.numeric(expected_means),
               info = "Mean column should contain correct mean for each group")
})

test_that("sum column contains correct sums", {
  df <- data.frame(category = c("A", "A", "B", "B", "B", "C"), value = c(10, 15, 10, 20, 30, 40))
  res <- aggregate_multiple(df, "category", "value")
  expected_sums <- c(A = sum(c(10, 15)), B = sum(c(10, 20, 30)), C = 40)
  rownames(expected_sums) <- NULL
  expect_equal(res$Sum[match(names(expected_sums), res$Group)], as.numeric(expected_sums),
               info = "Sum column should contain correct sum for each group")
})

test_that("sd column contains correct standard deviations", {
  df <- data.frame(category = c("A", "A", "B", "B", "B", "C"), value = c(10, 15, 10, 20, 30, 40))
  res <- aggregate_multiple(df, "category", "value")
  expected_sds <- c(A = sd(c(10, 15)), B = sd(c(10, 20, 30)), C = sd(40))
  rownames(expected_sds) <- NULL
  expect_equal(res$SD[match(names(expected_sds), res$Group)], as.numeric(expected_sds),
               info = "SD column should contain correct standard deviation for each group")
})

test_that("handles missing values in numeric column", {
  df <- data.frame(category = c("A", "A", "B", "B", "B", "C"), value = c(10, NA, 10, 20, 30, NA))
  res <- aggregate_multiple(df, "category", "value")
  expected_means <- c(A = mean(c(10, NA), na.rm = TRUE), B = mean(c(10, 20, 30)), C = mean(NA, na.rm = TRUE))
  expected_sums <- c(A = sum(c(10, NA), na.rm = TRUE), B = sum(c(10, 20, 30)), C = sum(NA, na.rm = TRUE))
  expected_sds <- c(A = sd(c(10, NA), na.rm = TRUE), B = sd(c(10, 20, 30)), C = sd(NA, na.rm = TRUE))
  expect_equal(res$Mean[match(names(expected_means), res$Group)], as.numeric(expected_means),
               info = "Mean should ignore NA values")
  expect_equal(res$Sum[match(names(expected_sums), res$Group)], as.numeric(expected_sums),
               info = "Sum should ignore NA values")
  expect_equal(res$SD[match(names(expected_sds), res$Group)], as.numeric(expected_sds),
               info = "SD should ignore NA values")
})

test_main.R

Master the essential R data structures used in exploratory data analysis (EDA), focusing on practical applications and hands-on challenges. This course is designed for learners already familiar with R syntax, core data structures, and data cleaning/wrangling techniques.

Explore the essential R data structures that power effective exploratory data analysis, with a focus on practical usage and hands-on challenges.

Challenge: Advanced Aggregation

Solution