import unittest
import psycopg2
import pandas as pd
import re

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_grouping_by_year_and_month(self):
        """Check if query groups by both year and month from order_date."""
        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)

        # Should have columns for year and month
        year_col = [col for col in result_df.columns if normalize_text(col) in ["order_year", "year"]]
        month_col = [col for col in result_df.columns if normalize_text(col) in ["order_month", "month"]]
        condition = len(year_col) == 1 and len(month_col) == 1
        _dynamic_test(
            self,
            condition,
            "Query groups by both year and month.",
            "Query does not group by both year and month or columns are missing."
        )

    def test_correct_order_counts(self):
        """Check if query returns correct count of orders for each year and month."""
        with open("query.sql", "r") as file:
            query = file.read()
        solution_query = '''
            SELECT EXTRACT(YEAR FROM order_date) AS order_year,
                   EXTRACT(MONTH FROM order_date) AS order_month,
                   COUNT(*) AS order_count
            FROM orders
            GROUP BY EXTRACT(YEAR FROM order_date), EXTRACT(MONTH FROM order_date)
            ORDER BY order_year, order_month
        '''
        self.cursor.execute(solution_query)
        expected_rows = self.cursor.fetchall()
        expected_columns = [desc[0] for desc in self.cursor.description]
        expected_df = pd.DataFrame(expected_rows, columns=expected_columns)

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

        # Normalize columns for comparison
        def get_col(df, names):
            for n in names:
                for col in df.columns:
                    if normalize_text(col) == n:
                        return col
            return None
        year_col = get_col(result_df, ["order_year", "year"])
        month_col = get_col(result_df, ["order_month", "month"])
        count_col = get_col(result_df, ["order_count", "count"])
        if not year_col or not month_col or not count_col:
            _dynamic_test(
                self,
                False,
                "",
                "Query result missing required columns."
            )
            return
        # Compare rows
        missing = []
        for _, row in expected_df.iterrows():
            mask = (
                (result_df[year_col] == row["order_year"]) &
                (result_df[month_col] == row["order_month"]) &
                (result_df[count_col] == row["order_count"])
            )
            if not mask.any():
                missing.append({"year": row["order_year"], "month": row["order_month"], "order_count": row["order_count"]})
        condition = len(missing) == 0
        fail_msg = "Missing or incorrect order counts for: " + str(missing) if missing else ""
        _dynamic_test(
            self,
            condition,
            "Query returns correct order counts for each year and month.",
            fail_msg
        )

    def test_all_months_present(self):
        """Check if query includes all months present in the data."""
        with open("query.sql", "r") as file:
            query = file.read()
        # Expected months: 2024-05 and 2024-06
        expected = set([(2024.0, 5.0), (2024.0, 6.0)])
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(rows, columns=columns)
        year_col = [col for col in result_df.columns if normalize_text(col) in ["order_year", "year"]][0]
        month_col = [col for col in result_df.columns if normalize_text(col) in ["order_month", "month"]][0]
        found = set(zip(result_df[year_col], result_df[month_col]))
        missing = expected - found
        condition = len(missing) == 0
        _dynamic_test(
            self,
            condition,
            "Query includes all months present in the data.",
            f"Missing months in result: {missing}"
        )

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

Master the use of built-in SQL functions to manipulate strings, dates, numbers, logical values, nulls, and JSON data. This module provides a hands-on approach to understanding and applying SQL functions in real-world scenarios, enhancing your data querying and transformation skills.

Explore SQL's powerful string functions for manipulating and analyzing textual data in databases.

Challenge: Monthly Order Summary

Ratkaisu