Summary  
This chapter covers the use of the AVG() aggregate function to compute average values over entire columns or filtered subsets within SQL queries.

General domain of usage  
Relational database querying

`AVG()` returns the average value of a certain column. 
Let's see an example: 

`AVG()` can also be used to find the average of a selected set of columns or rows that meet certain conditions. Here’s an example:

SELECT AVG(population) 
FROM country
WHERE population < 4478500;

import unittest
import psycopg2
import pandas as pd
import decimal

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_avg_surfacearea_correctness(self):
        """Check that the query returns the correct average of the surfacearea column from country table."""
        with open("query.sql", "r") as file:
            query = file.read()
        # Calculate expected average
        self.cursor.execute("SELECT surfacearea FROM country")
        surfaceareas = [row[0] for row in self.cursor.fetchall() if row[0] is not None]
        expected_avg = sum(surfaceareas) / len(surfaceareas) if surfaceareas else None

        self.cursor.execute(query)
        result = self.cursor.fetchone()[0]
        # Accept float rounding error up to 6 decimals
        if isinstance(result, decimal.Decimal):
            result_float = float(result)
        else:
            result_float = result
        if isinstance(expected_avg, decimal.Decimal):
            expected_avg_float = float(expected_avg)
        else:
            expected_avg_float = expected_avg
        condition = expected_avg is not None and abs(result_float - expected_avg_float) < 1e-6
        _dynamic_test(
            self,
            condition,
            "Query returns the correct average value of surfacearea.",
            f"Expected average: {expected_avg}, but got: {result}."
        )

    def test_query_uses_avg_function(self):
        """Check that the query uses the AVG() function."""
        with open("query.sql", "r") as file:
            query = file.read()
        condition = "avg" in query.lower()
        _dynamic_test(
            self,
            condition,
            "Query uses the AVG() function.",
            "Query does not use the AVG() function."
        )

    def test_query_uses_select(self):
        """Check that the query uses the SELECT statement."""
        with open("query.sql", "r") as file:
            query = file.read()
        condition = query.strip().lower().startswith("select")
        _dynamic_test(
            self,
            condition,
            "Query uses the SELECT statement.",
            "Query does not use the SELECT statement."
        )

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 AVG() Function

Lösning