import unittest
import user_code as uc


def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)


class TestSQLChallenge(unittest.TestCase):

    def test_top_routes_by_length(self):
        _dynamic_test(self,
            isinstance(uc.top_routes_by_length, list) and len(uc.top_routes_by_length) == 3 and all(len(r) == 3 for r in uc.top_routes_by_length),
            "The `top_routes_by_length` is a list of 3 tuples.",
            "Expected `top_routes_by_length` to be a list of 3 tuples.")

    def test_longest_flight_columns(self):
        _dynamic_test(self,
            {"Airline", "Flight", "Length"}.issubset(set(uc.longest_flight_per_airline.columns)),
            "The `longest_flight_per_airline` contains required columns.",
            "Expected `longest_flight_per_airline` to have Airline, Flight, Length columns.")

    def test_delays_by_dow(self):
        _dynamic_test(self,
            isinstance(uc.delays_by_dow, list) and len(uc.delays_by_dow) > 0 and all(len(r) == 2 for r in uc.delays_by_dow),
            "The `delays_by_dow` is a non-empty list of 2-element tuples.",
            "Expected `delays_by_dow` to be a non-empty list of 2-element tuples.")

    def test_delays_by_dow_sorted(self):
        days = [r[0] for r in uc.delays_by_dow]
        _dynamic_test(self,
            days == sorted(days),
            "The `delays_by_dow` is sorted by DayOfWeek ascending.",
            "Expected `delays_by_dow` to be sorted by DayOfWeek ascending.")


if __name__ == "__main__":
    unittest.main()

test_main.py

Master the essentials of data processing using PySpark, focusing on reading and writing data, cleaning and transforming datasets, leveraging Spark SQL, and optimizing performance for large-scale analytics.

Core concepts and practical skills for data processing with PySpark, from data ingestion to advanced SQL analytics and performance optimization.

Challenge: Analyzing Sales Data with Spark SQL

Oplossing