After exploring the basics of logical functions and their application in SQL, you are ready to take on a practical challenge that puts your understanding to the test. In real-world scenarios, it is common to categorize transactions by their amount to quickly identify high-value, medium-value, or low-value activities. This kind of classification is particularly useful for business analytics, fraud detection, and reporting.

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_all_rows_returned(self):
        """Check that all rows from transactions are returned."""
        with open("query.sql", "r") as file:
            query = file.read()

        self.cursor.execute("SELECT COUNT(*) FROM transactions;")
        expected_count = self.cursor.fetchone()[0]
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        _dynamic_test(
            self,
            len(rows) == expected_count,
            f"All {expected_count} rows are returned.",
            f"Expected {expected_count} rows, got {len(rows)}."
        )

    def test_amount_category_column_exists(self):
        """Check that amount_category column exists in result."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        columns = [desc[0] for desc in self.cursor.description]
        _dynamic_test(
            self,
            "amount_category" in columns,
            "amount_category column is present.",
            "amount_category column is missing."
        )

    def test_high_category(self):
        """Transactions with amount >= 300 are labeled 'High'."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(rows, columns=columns)
        high_df = df[df["amount"] >= 300]
        condition = all(high_df["amount_category"] == "High")
        _dynamic_test(
            self,
            condition,
            "All transactions with amount >= 300 are labeled 'High'.",
            "Some transactions with amount >= 300 are not labeled 'High'."
        )

    def test_medium_category(self):
        """Transactions with amount >= 100 and < 300 are labeled 'Medium'."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(rows, columns=columns)
        medium_df = df[(df["amount"] >= 100) & (df["amount"] < 300)]
        condition = all(medium_df["amount_category"] == "Medium")
        _dynamic_test(
            self,
            condition,
            "All transactions with amount >= 100 and < 300 are labeled 'Medium'.",
            "Some transactions with amount >= 100 and < 300 are not labeled 'Medium'."
        )

    def test_low_category(self):
        """Transactions with amount < 100 are labeled 'Low'."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(rows, columns=columns)
        low_df = df[df["amount"] < 100]
        condition = all(low_df["amount_category"] == "Low")
        _dynamic_test(
            self,
            condition,
            "All transactions with amount < 100 are labeled 'Low'.",
            "Some transactions with amount < 100 are not labeled 'Low'."
        )

    def test_all_transactions_present(self):
        """Check that all transaction_ids are present in result."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        result_rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(result_rows, columns=columns)
        self.cursor.execute("SELECT transaction_id FROM transactions;")
        expected_ids = set([row[0] for row in self.cursor.fetchall()])
        returned_ids = set(result_df["transaction_id"])
        condition = expected_ids == returned_ids
        _dynamic_test(
            self,
            condition,
            "All transaction_ids are present in result.",
            f"Missing transaction_ids: {expected_ids - returned_ids}"
        )

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

This beginner course focuses on the essential SQL functions used for data cleaning and transformation. Learners will practice handling missing values, formatting and standardizing data, and applying string, date, numeric, logical, and null handling functions to prepare datasets for analysis. The course provides hands-on challenges directly related to the most common data preparation tasks in SQL.

Challenge: Categorize Transactions

解答