Summary  
This chapter covers using the DISTINCT keyword in SELECT statements to retrieve unique values by filtering out duplicates.

General domain of usage  
Relational database querying

Note that the `SELECT` statement returns all rows in a given column. However, what if we don't need all the values from a column, especially when they are duplicated, and we only need **unique values**? 

For such cases, it is convenient to use the keyword `DISTINCT`, placed immediately before the column names. Let's take a look at an example:

import unittest
import psycopg2
import pandas as pd

class TestTask(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_correct_distinct_continents(self):
        """Check that the query returns the correct set of distinct continents from country table."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Get expected distinct continents from the table
        self.cursor.execute("SELECT DISTINCT continent FROM country;")
        expected_rows = self.cursor.fetchall()
        expected_set = set([row[0] for row in expected_rows])

        # Run user's query
        self.cursor.execute(query)
        user_rows = self.cursor.fetchall()
        user_set = set([row[0] for row in user_rows])

        condition = user_set == expected_set
        _dynamic_test(
            self,
            condition,
            "Query returns the correct set of distinct continent values.",
            f"Query did not return the correct set of distinct continent values.\\nExpected: {expected_set}\\nGot: {user_set}"
        )

    def test_query_uses_distinct_keyword(self):
        """Check that the query uses the DISTINCT keyword."""
        with open("query.sql", "r") as file:
            query = file.read()
        condition = "distinct" in query.lower()
        _dynamic_test(
            self,
            condition,
            "Query uses the DISTINCT keyword.",
            "Query does not use the DISTINCT keyword."
        )

    def test_query_selects_continent_column(self):
        """Check that the query selects the continent column."""
        with open("query.sql", "r") as file:
            query = file.read()
        # Accepts "continent" or "(continent)"
        condition = "continent" in query.lower()
        _dynamic_test(
            self,
            condition,
            "Query selects the 'continent' column.",
            "Query does not select the 'continent' column."
        )

    def test_query_from_country_table(self):
        """Check that the query selects from the country table."""
        with open("query.sql", "r") as file:
            query = file.read()
        condition = "from country" in query.lower().replace("\\n", " ").replace("\t", " ")
        _dynamic_test(
            self,
            condition,
            "Query selects from the 'country' table.",
            "Query does not select from the 'country' table."
        )

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

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.

Retrieving Distinct Rows

Lösung