Summary  
This chapter covers the use of an aggregate function to compute the sum of values in a column based on a filter condition.

General domain of usage  
Relational database querying and data aggregation.

`SUM()` returns the total of all the values in a given column. 

Here's an example:

SELECT SUM(population) 
FROM country 
WHERE continent='Asia';

The `SUM()` function calculates the total population of all Asian countries found in the `country` table.

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_sum_function_used(self):
        """Check that SUM() is used in the query."""
        with open("query.sql", "r") as file:
            query = file.read()
        condition = "sum" in query.lower()
        _dynamic_test(
            self,
            condition,
            "SUM() function is used in the query.",
            "SUM() function is not used in the query."
        )
    def test_correct_total_surfacearea(self):
        """Check that the result is the correct sum of surfacearea for Europe."""
        # Calculate expected sum based on init script
        europe_rows = [
            64589,    # Latvia
            41526,    # Netherlands
            91982,    # Portugal
            449964,   # Sweden
            603700,   # Ukraine
            323877,   # Norway
            1.50,     # Monaco
            316       # Malta
        ]
        # The database stores Monaco's surface area as 2 (not 1.5), so adjust expected sum accordingly
        expected_sum = sum([64589, 41526, 91982, 449964, 603700, 323877, 2, 316])

        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        result = self.cursor.fetchone()
        # result is tuple like (sum,)
        if result is not None:
            user_sum = float(result[0])
        else:
            user_sum = None
        # Allow small error due to float
        condition = user_sum is not None and abs(user_sum - expected_sum) < 0.01
        _dynamic_test(
            self,
            condition,
            f"Query returns the correct sum of surfacearea for Europe: {expected_sum}.",
            f"Query does not return the correct sum for Europe. Expected: {expected_sum}, Got: {user_sum}"
        )

    def test_no_extra_rows(self):
        """Check that only one row is returned."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        condition = len(rows) == 1
        _dynamic_test(
            self,
            condition,
            "Query returns a single row as expected.",
            f"Query returned {len(rows)} rows instead of 1."
        )

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):
    import re
    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

Focuses on practical SQL skills for filtering data with WHERE, sorting results with ORDER BY, and summarizing information using GROUP BY and aggregate functions. Hands-on challenges reinforce each concept, preparing learners to analyze and summarize real-world datasets effectively.

The SUM() Function

Solution