import unittest
import psycopg2
import pandas as pd

class TestPostgresQuery(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.connection = psycopg2.connect(
            host="localhost",
            user="agent",
            password="qwerty",
            dbname="testdb",
            sslmode="disable"
        )
        cls.cursor = cls.connection.cursor()

    def test_no_employee_with_recent_salary(self):
        """Returns only employees who have no salary record with a salary_date on or after '2023-04-27'."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Get all employees who have a salary record on or after '2023-04-27'
        self.cursor.execute("""
            SELECT DISTINCT employee_id
            FROM salaries
            WHERE salary_date >= '2023-04-27'
        """)
        employees_with_recent_salary = set(row[0] for row in self.cursor.fetchall())

        # Run user query
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(rows, columns=columns)

        # Ensure none of the returned employees have a recent salary
        returned_ids = set(result_df['employee_id'].tolist())
        intersection = returned_ids & employees_with_recent_salary
        _dynamic_test(
            self,
            len(intersection) == 0,
            "No employee with a recent salary is returned.",
            f"The following employee_ids have a salary record on or after 2023-04-27 but were returned: {intersection}"
        )

    def test_all_eligible_employees_included(self):
        """Includes all employees who have no salary record with a salary_date on or after '2023-04-27'."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Get all employees who have NO salary record on or after '2023-04-27'
        self.cursor.execute("""
            SELECT employee_id, name FROM employees
            WHERE employee_id NOT IN (
                SELECT DISTINCT employee_id FROM salaries WHERE salary_date >= '2023-04-27'
            )
            ORDER BY employee_id
        """)
        expected = self.cursor.fetchall()
        expected_set = set(expected)

        self.cursor.execute(query)
        result = self.cursor.fetchall()
        result_set = set(result)

        missing = expected_set - result_set
        _dynamic_test(
            self,
            len(missing) == 0,
            "All eligible employees are included.",
            f"The following eligible employees were not returned: {missing}"
        )

    def test_no_extra_employees(self):
        """Does not include any employee who has a salary record dated on or after '2023-04-27'."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Employees who should be returned
        self.cursor.execute("""
            SELECT employee_id FROM employees
            WHERE employee_id NOT IN (
                SELECT DISTINCT employee_id FROM salaries WHERE salary_date >= '2023-04-27'
            )
        """)
        expected_ids = set(row[0] for row in self.cursor.fetchall())

        self.cursor.execute(query)
        result = self.cursor.fetchall()
        result_ids = set(row[0] for row in result)

        extra = result_ids - expected_ids
        _dynamic_test(
            self,
            len(extra) == 0,
            "No extra employees are included.",
            f"The following employee_ids were returned but should not be: {extra}"
        )

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

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

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


test_solution.py

Master the art of writing and applying subqueries in SQL through real-world scenarios. This module covers the theory and practice of subqueries, including their use in SELECT, WHERE, and FROM clauses, as well as correlated subqueries. 

Explore subqueries using an e-commerce dataset, focusing on orders, customers, and products. Learn to extract insights and solve business problems using subqueries.

Challenge: Employees Without Recent Salary Increase

Solution