{
  "task_name": "advanced_analytics",
  "difficulty": "hard",
  "description": "Subqueries, CTEs, window functions, and complex multi-table analytics",
  "max_steps_per_question": 5,
  "questions": [
    {
      "id": "hard_1",
      "question": "Find all customers whose total spending across all orders exceeds the average total spending per customer. Show customer name and total spent, sorted by total spent from highest to lowest.",
      "ground_truth_sql": "SELECT c.name, SUM(o.total_amount) as total_spent FROM customers c JOIN orders o ON c.id = o.customer_id GROUP BY c.id HAVING total_spent > (SELECT AVG(total_spent) FROM (SELECT SUM(total_amount) as total_spent FROM orders GROUP BY customer_id)) ORDER BY total_spent DESC",
      "expected_columns": ["name", "total_spent"],
      "expected_row_count": 9,
      "expected_rows": [
        ["Vikram Singh", 7296.0],
        ["Kavita Joshi", 6497.0],
        ["Rahul Kumar", 5797.0],
        ["Divya Saxena", 5197.0],
        ["Priya Patel", 5097.0],
        ["Swati Tiwari", 3798.0],
        ["Pooja Mishra", 3499.0],
        ["Aarav Sharma", 3497.0],
        ["Meera Iyer", 3448.0]
      ],
      "order_matters": true
    },
    {
      "id": "hard_2",
      "question": "Rank all products by their total revenue (quantity * unit_price from order_items) within each product category. Show category, product name, revenue, and the rank within the category. Sort by category alphabetically, then by rank.",
      "ground_truth_sql": "SELECT p.category, p.name, SUM(oi.quantity * oi.unit_price) as revenue, RANK() OVER (PARTITION BY p.category ORDER BY SUM(oi.quantity * oi.unit_price) DESC) as category_rank FROM products p JOIN order_items oi ON p.id = oi.product_id GROUP BY p.id ORDER BY p.category, category_rank",
      "expected_columns": ["category", "name", "revenue", "category_rank"],
      "expected_row_count": 15,
      "expected_rows": [
        ["Books", "Python Programming", 1796.0, 1],
        ["Books", "Data Science Handbook", 1398.0, 2],
        ["Books", "Cooking Recipes", 1197.0, 3],
        ["Books", "Mystery Novel", 598.0, 4],
        ["Clothing", "Running Shoes", 11996.0, 1],
        ["Clothing", "Winter Jacket", 3499.0, 2],
        ["Clothing", "Denim Jeans", 2998.0, 3],
        ["Clothing", "Cotton T-Shirt", 2396.0, 4],
        ["Electronics", "Wireless Headphones", 17493.0, 1],
        ["Electronics", "Bluetooth Speaker", 7998.0, 2],
        ["Electronics", "Smartphone Case", 2495.0, 3],
        ["Electronics", "USB-C Cable", 398.0, 4],
        ["Home", "Desk Lamp", 5196.0, 1],
        ["Home", "Ceramic Mug Set", 4794.0, 2],
        ["Home", "Plant Pot", 349.0, 3]
      ],
      "order_matters": true
    },
    {
      "id": "hard_3",
      "question": "Calculate the month-over-month growth in order count for 2024. Show the month (as YYYY-MM), the number of orders that month, and the change from the previous month (NULL for the first month). Sort by month.",
      "ground_truth_sql": "SELECT strftime('%Y-%m', order_date) as month, COUNT(*) as order_count, COUNT(*) - LAG(COUNT(*)) OVER (ORDER BY strftime('%Y-%m', order_date)) as growth FROM orders GROUP BY month ORDER BY month",
      "expected_columns": ["month", "order_count", "growth"],
      "expected_row_count": 6,
      "expected_rows": [
        ["2024-01", 6, null],
        ["2024-02", 6, 0],
        ["2024-03", 7, 1],
        ["2024-04", 4, -3],
        ["2024-05", 4, 0],
        ["2024-06", 3, -1]
      ],
      "order_matters": true
    },
    {
      "id": "hard_4",
      "question": "Find all customers who have purchased products from at least 3 different product categories. Show the customer name and the number of distinct categories they bought from, sorted by category count descending then name ascending.",
      "ground_truth_sql": "SELECT c.name, COUNT(DISTINCT p.category) as category_count FROM customers c JOIN orders o ON c.id = o.customer_id JOIN order_items oi ON o.id = oi.order_id JOIN products p ON oi.product_id = p.id GROUP BY c.id HAVING category_count >= 3 ORDER BY category_count DESC, c.name ASC",
      "expected_columns": ["name", "category_count"],
      "expected_row_count": 5,
      "expected_rows": [
        ["Rahul Kumar", 4],
        ["Ananya Reddy", 3],
        ["Priya Patel", 3],
        ["Ritu Chopra", 3],
        ["Rohan Das", 3]
      ],
      "order_matters": true
    },
    {
      "id": "hard_5",
      "question": "For each product category, find the product with the highest average review rating. Show the category, product name, and average rating (rounded to 2 decimal places). Only include products that have at least 2 reviews. Sort by category alphabetically, then by average rating descending.",
      "ground_truth_sql": "SELECT p.category, p.name, ROUND(AVG(r.rating), 2) as avg_rating FROM products p JOIN reviews r ON p.id = r.product_id GROUP BY p.id HAVING COUNT(r.id) >= 2 ORDER BY p.category, avg_rating DESC",
      "expected_columns": ["category", "name", "avg_rating"],
      "expected_row_count": 8,
      "expected_rows": [
        ["Books", "Python Programming", 4.5],
        ["Clothing", "Running Shoes", 4.67],
        ["Clothing", "Cotton T-Shirt", 3.5],
        ["Electronics", "Wireless Headphones", 4.67],
        ["Electronics", "Bluetooth Speaker", 4.5],
        ["Electronics", "Smartphone Case", 3.5],
        ["Home", "Ceramic Mug Set", 4.67],
        ["Home", "Desk Lamp", 4.5]
      ],
      "order_matters": true
    }
  ]
}