
library(testthat)

source("user_code.R")
test_that("performs correct inner join with duplicates", {
  df1 <- data.frame(ID = c(1, 2, 2, 3, 4), Value1 = c("A", "B", "C", "D", "E"))
  df2 <- data.frame(ID = c(2, 2, 3, 5), Value2 = c("W", "X", "Y", "Z"))
  result <- merge_inner_handle_duplicates(df1, df2, "ID")
  expect_true(is.data.frame(result), "Result should be a data frame.")
  expect_true(all(c("ID", "Value1", "Value2") %in% colnames(result)), "All expected columns should be present.")
  # Check all valid combinations for ID=2
  id2_rows <- subset(result, ID == 2)
  expect_equal(nrow(id2_rows), 4, info = "Should have 4 combinations for ID=2 (2x2)")
  expect_true(all(id2_rows$Value1 %in% c("B", "C")), info = "Value1 for ID=2 should be B or C.")
  expect_true(all(id2_rows$Value2 %in% c("W", "X")), info = "Value2 for ID=2 should be W or X.")
  # Check ID=3
  id3_rows <- subset(result, ID == 3)
  expect_equal(nrow(id3_rows), 1, info = "Should have 1 row for ID=3.")
  expect_equal(as.character(id3_rows$Value1), "D", info = "Value1 for ID=3 should be D.")
  expect_equal(as.character(id3_rows$Value2), "Y", info = "Value2 for ID=3 should be Y.")
  # Should not contain ID=1,4,5
  expect_false(any(result$ID %in% c(1,4,5)), info = "Result should not contain IDs only present in one data frame.")
})

test_that("works with different order and duplicates in both frames", {
  df1 <- data.frame(ID = c(2, 3, 2, 6), Value1 = c("A", "B", "C", "D"))
  df2 <- data.frame(ID = c(3, 2, 2, 7), Value2 = c("X", "Y", "Z", "W"))
  result <- merge_inner_handle_duplicates(df1, df2, "ID")
  # For ID=2, df1 has 2 rows, df2 has 2 rows => 4 combinations
  id2_rows <- subset(result, ID == 2)
  expect_equal(nrow(id2_rows), 4, info = "Should have 4 combinations for ID=2.")
  expect_true(all(id2_rows$Value1 %in% c("A", "C")), info = "Value1 for ID=2 should be A or C.")
  expect_true(all(id2_rows$Value2 %in% c("Y", "Z")), info = "Value2 for ID=2 should be Y or Z.")
  # For ID=3, only one combination
  id3_rows <- subset(result, ID == 3)
  expect_equal(nrow(id3_rows), 1, info = "Should have 1 row for ID=3.")
  expect_equal(as.character(id3_rows$Value1), "B", info = "Value1 for ID=3 should be B.")
  expect_equal(as.character(id3_rows$Value2), "X", info = "Value2 for ID=3 should be X.")
  # Should not contain ID=6 or 7
  expect_false(any(result$ID %in% c(6,7)), info = "Result should not contain IDs only present in one data frame.")
})

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: Merging and Joining

Ratkaisu