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_selects_order_id_and_order_date(self):
        """Check if order_id and order_date columns are present in the 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,
            'order_id' in columns and 'order_date' in columns,
            "Result contains both 'order_id' and 'order_date' columns.",
            "Result does not contain both 'order_id' and 'order_date' columns."
        )

    def test_days_since_order_column_present(self):
        """Check if days_since_order column is present in the 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,
            'days_since_order' in columns,
            "Result contains 'days_since_order' column.",
            "Result does not contain 'days_since_order' column."
        )

    def test_days_since_order_is_correct(self):
        """Check if days_since_order is the difference between CURRENT_DATE and order_date for each row."""
        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]
        result_df = pd.DataFrame(rows, columns=columns)

        # Get current date from database for consistency
        self.cursor.execute("SELECT CURRENT_DATE;")
        current_date = self.cursor.fetchone()[0]

        self.cursor.execute("SELECT order_id, order_date FROM orders;")
        orders = self.cursor.fetchall()
        expected = {}
        for order_id, order_date in orders:
            expected[order_id] = (current_date - order_date).days

        mismatch = []
        for _, row in result_df.iterrows():
            oid = row['order_id']
            days = row['days_since_order']
            if oid in expected and days != expected[oid]:
                mismatch.append((oid, days, expected[oid]))
        condition = len(mismatch) == 0
        if not condition:
            mismatch_str = "\\n".join(f"order_id={oid}: got {got}, expected {exp}" for oid, got, exp in mismatch)
            failure_msg = f"Incorrect days_since_order values:\\n{mismatch_str}"
        else:
            failure_msg = ""
        _dynamic_test(
            self,
            condition,
            "days_since_order values are correct.",
            failure_msg
        )

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: Calculate Order Age

解答