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_row_count_matches_sales(self):
        """Check that the query returns one row per sale."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT COUNT(*) FROM sales;")
        sales_count = self.cursor.fetchone()[0]
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        _dynamic_test(
            self,
            len(result) == sales_count,
            "Returned row count matches sales table.",
            f"Expected {sales_count} rows, got {len(result)}."
        )

    def test_customer_name_combined_correctly(self):
        """Check that the customer_name column is correctly combined."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(result, columns=columns)
        self.cursor.execute("SELECT s.sale_id, c.first_name, c.last_name FROM sales s JOIN customers c ON s.customer_id = c.customer_id;")
        expected = self.cursor.fetchall()
        correct = True
        for sale_id, first, last in expected:
            customer_name = f"{first} {last}"
            # Find row in df with this customer_name
            if not (df['customer_name'] == customer_name).any():
                correct = False
                break
        _dynamic_test(
            self,
            correct,
            "Customer names are correctly combined.",
            "Some customer names are not combined correctly."
        )

    def test_product_name_matches(self):
        """Check that product_name matches the product for each sale."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(result, columns=columns)
        self.cursor.execute("SELECT s.sale_id, p.product_name FROM sales s JOIN products p ON s.product_id = p.product_id;")
        expected = self.cursor.fetchall()
        correct = True
        for sale_id, product_name in expected:
            if not (df['product_name'] == product_name).any():
                correct = False
                break
        _dynamic_test(
            self,
            correct,
            "Product names match for each sale.",
            "Some product names do not match the sale."
        )

    def test_quantity_matches_sales(self):
        """Check that quantity matches the value in the sales table for each sale."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(result, columns=columns)
        self.cursor.execute("SELECT c.first_name || ' ' || c.last_name AS customer_name, p.product_name, s.quantity FROM sales s JOIN customers c ON s.customer_id = c.customer_id JOIN products p ON s.product_id = p.product_id;")
        expected = self.cursor.fetchall()
        expected_df = pd.DataFrame(expected, columns=['customer_name', 'product_name', 'quantity'])
        # For each expected row, check if there is a matching row in df
        mismatch = False
        for _, row in expected_df.iterrows():
            mask = (
                (df['customer_name'] == row['customer_name']) &
                (df['product_name'] == row['product_name']) &
                (df['quantity'] == row['quantity'])
            )
            if not mask.any():
                mismatch = True
                break
        _dynamic_test(
            self,
            not mismatch,
            "Quantities match for each sale.",
            "Some quantities do not match the sales 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

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：Product Purchase Details

解答