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_sales_records_present(self):
        """Check that all sales records are present and paired with correct customer names."""
        with open("query.sql", "r") as file:
            query = file.read()
        solution_query = '''
        SELECT customers.first_name, customers.last_name, sales.quantity
        FROM customers JOIN sales ON customers.customer_id = sales.customer_id
        '''
        self.cursor.execute(solution_query)
        solution_rows = self.cursor.fetchall()
        solution_columns = [desc[0] for desc in self.cursor.description]
        solution_df = pd.DataFrame(solution_rows, columns=solution_columns)

        self.cursor.execute(query)
        user_rows = self.cursor.fetchall()
        user_columns = [desc[0] for desc in self.cursor.description]
        user_df = pd.DataFrame(user_rows, columns=user_columns)

        missing_rows = []
        for _, expected_row in solution_df.iterrows():
            mask = (
                (user_df['first_name'] == expected_row['first_name']) &
                (user_df['last_name'] == expected_row['last_name']) &
                (user_df['quantity'] == expected_row['quantity'])
            )
            if not mask.any():
                missing_rows.append(expected_row.to_dict())
        condition = len(missing_rows) == 0
        if not condition:
            missing_str = '\\n'.join(str(row) for row in missing_rows)
            failure_msg = f"The following expected rows are missing from your result:\\n{missing_str}"
        else:
            failure_msg = ""
        _dynamic_test(
            self,
            condition,
            "All sales records are present and paired with correct customer names.",
            failure_msg
        )

    def test_no_extra_rows(self):
        """Check that only sales with a matching customer record are included."""
        with open("query.sql", "r") as file:
            query = file.read()
        solution_query = '''
        SELECT customers.first_name, customers.last_name, sales.quantity
        FROM customers JOIN sales ON customers.customer_id = sales.customer_id
        '''
        self.cursor.execute(solution_query)
        solution_rows = self.cursor.fetchall()
        solution_columns = [desc[0] for desc in self.cursor.description]
        solution_df = pd.DataFrame(solution_rows, columns=solution_columns)

        self.cursor.execute(query)
        user_rows = self.cursor.fetchall()
        user_columns = [desc[0] for desc in self.cursor.description]
        user_df = pd.DataFrame(user_rows, columns=user_columns)

        extra_rows = []
        for _, user_row in user_df.iterrows():
            mask = (
                (solution_df['first_name'] == user_row['first_name']) &
                (solution_df['last_name'] == user_row['last_name']) &
                (solution_df['quantity'] == user_row['quantity'])
            )
            if not mask.any():
                extra_rows.append(user_row.to_dict())
        condition = len(extra_rows) == 0
        if not condition:
            extra_str = '\\n'.join(str(row) for row in extra_rows)
            failure_msg = f"Your result contains extra/unexpected rows:\\n{extra_str}"
        else:
            failure_msg = ""
        _dynamic_test(
            self,
            condition,
            "No extra/unexpected rows are present in the result.",
            failure_msg
        )

    def test_quantity_matches_sales_table(self):
        """Check that the quantity value for each sale matches the sales table."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        user_rows = self.cursor.fetchall()
        user_columns = [desc[0] for desc in self.cursor.description]
        user_df = pd.DataFrame(user_rows, columns=user_columns)

        self.cursor.execute("SELECT sale_id, customer_id, quantity FROM sales")
        sales_rows = self.cursor.fetchall()
        sales_df = pd.DataFrame(sales_rows, columns=["sale_id", "customer_id", "quantity"])
        self.cursor.execute("SELECT customer_id, first_name, last_name FROM customers")
        cust_rows = self.cursor.fetchall()
        cust_df = pd.DataFrame(cust_rows, columns=["customer_id", "first_name", "last_name"])
        merged = pd.merge(sales_df, cust_df, how="inner", on="customer_id")

        mismatch = []
        for _, row in merged.iterrows():
            mask = (
                (user_df['first_name'] == row['first_name']) &
                (user_df['last_name'] == row['last_name']) &
                (user_df['quantity'] == row['quantity'])
            )
            if not mask.any():
                mismatch.append({
                    "first_name": row['first_name'],
                    "last_name": row['last_name'],
                    "quantity": row['quantity']
                })
        condition = len(mismatch) == 0
        if not condition:
            mismatch_str = '\\n'.join(str(row) for row in mismatch)
            failure_msg = f"The following (name, quantity) pairs are missing or incorrect:\\n{mismatch_str}"
        else:
            failure_msg = ""
        _dynamic_test(
            self,
            condition,
            "Quantity value for each sale matches the sales table.",
            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

実践的なデータ分析スキルに焦点を当て、SQLを基礎から学べる包括的で初心者向けのコースです。分かりやすい解説、実際の事例、実践的な課題を通じて、SQLを用いたデータのクエリ、変換、分析を習得します。

リレーショナルデータベースとSQLの基礎概念を学習します。テーブルからデータを取得、フィルタリング、並べ替える方法を探求し、より高度なデータ分析の基礎を築きます。

SQLの強力な集計機能を深く学びます。データを要約し、グループ化し、より深い洞察のために分析する方法を習得します。

複数のテーブルからデータを組み合わせる力を引き出します。さまざまな種類の結合を実行し、複雑なビジネス上の質問に答える方法を学びます。

サブクエリ、ウィンドウ関数、データ変換などを含む高度なSQL技術を習得し、強力なデータ分析を実現します。

チャレンジ：カスタマーセールスレポート

解答