데이터 분석가 면접을 위한 고급 SQL: 서브쿼리, 피벗, 쿼리 최적화 완벽 가이드 (2026년)

-- regular_subquery_threshold.sql
-- Find all orders above the average order value
SELECT
  order_id,
  customer_id,
  total_amount
FROM orders
WHERE total_amount > (
  -- Executes once, returns a single scalar value
  SELECT AVG(total_amount)
  FROM orders
);

-- correlated_subquery_department.sql
-- Employees earning above their department average
SELECT
  e.employee_id,
  e.name,
  e.department,
  e.salary
FROM employees e
WHERE e.salary > (
  -- Re-evaluated for each employee's department
  SELECT AVG(e2.salary)
  FROM employees e2
  WHERE e2.department = e.department
);

-- optimized_with_cte.sql
-- Same result, single pass over the data
WITH dept_avg AS (
  SELECT
    department,
    AVG(salary) AS avg_salary
  FROM employees
  GROUP BY department
)
SELECT
  e.employee_id,
  e.name,
  e.department,
  e.salary
FROM employees e
JOIN dept_avg d ON e.department = d.department
WHERE e.salary > d.avg_salary;

-- exists_vs_in.sql
-- Customers who placed at least one order in 2026 (EXISTS — preferred)
SELECT c.customer_id, c.name
FROM customers c
WHERE EXISTS (
  SELECT 1
  FROM orders o
  WHERE o.customer_id = c.customer_id
    AND o.order_date >= '2026-01-01'
);

-- Equivalent with IN (slower on large datasets)
SELECT customer_id, name
FROM customers
WHERE customer_id IN (
  SELECT customer_id
  FROM orders
  WHERE order_date >= '2026-01-01'
);

-- scalar_subquery_select.sql
-- Each product with its category's total revenue
SELECT
  p.product_id,
  p.product_name,
  p.category,
  (
    SELECT SUM(oi.quantity * oi.unit_price)
    FROM order_items oi
    JOIN products p2 ON oi.product_id = p2.product_id
    WHERE p2.category = p.category
  ) AS category_total_revenue
FROM products p;

-- pivot_monthly_revenue.sql
-- Monthly revenue pivot: one row per product, one column per month
SELECT
  product_id,
  product_name,
  SUM(CASE WHEN EXTRACT(MONTH FROM order_date) = 1
    THEN quantity * unit_price ELSE 0 END) AS jan_revenue,
  SUM(CASE WHEN EXTRACT(MONTH FROM order_date) = 2
    THEN quantity * unit_price ELSE 0 END) AS feb_revenue,
  SUM(CASE WHEN EXTRACT(MONTH FROM order_date) = 3
    THEN quantity * unit_price ELSE 0 END) AS mar_revenue,
  SUM(CASE WHEN EXTRACT(MONTH FROM order_date) = 4
    THEN quantity * unit_price ELSE 0 END) AS apr_revenue,
  -- Repeat for remaining months
  SUM(quantity * unit_price) AS total_revenue
FROM order_items oi
JOIN orders o ON oi.order_id = o.order_id
JOIN products p ON oi.product_id = p.product_id
WHERE o.order_date >= '2026-01-01'
GROUP BY product_id, product_name
ORDER BY total_revenue DESC;

-- pivot_user_activity.sql
-- User activity: sessions by day of week and device type
SELECT
  user_id,
  COUNT(CASE WHEN device_type = 'mobile' THEN 1 END) AS mobile_sessions,
  COUNT(CASE WHEN device_type = 'desktop' THEN 1 END) AS desktop_sessions,
  COUNT(CASE WHEN device_type = 'tablet' THEN 1 END) AS tablet_sessions,
  ROUND(
    COUNT(CASE WHEN device_type = 'mobile' THEN 1 END) * 100.0 / COUNT(*),
    1
  ) AS mobile_pct
FROM user_sessions
WHERE session_date >= CURRENT_DATE - INTERVAL '30 days'
GROUP BY user_id
HAVING COUNT(*) >= 5  -- Only users with meaningful activity
ORDER BY mobile_pct DESC;

-- crosstab_dynamic_pivot.sql
-- Enable the extension (once per database)
CREATE EXTENSION IF NOT EXISTS tablefunc;

-- Revenue by product and quarter using CROSSTAB
SELECT *
FROM crosstab(
  $$
    SELECT
      product_name,
      'Q' || EXTRACT(QUARTER FROM order_date)::TEXT AS quarter,
      SUM(quantity * unit_price) AS revenue
    FROM order_items oi
    JOIN orders o ON oi.order_id = o.order_id
    JOIN products p ON oi.product_id = p.product_id
    WHERE EXTRACT(YEAR FROM o.order_date) = 2026
    GROUP BY product_name, quarter
    ORDER BY product_name, quarter
  $$,
  $$ VALUES ('Q1'), ('Q2'), ('Q3'), ('Q4') $$
) AS pivot_table(
  product_name TEXT,
  q1_revenue NUMERIC,
  q2_revenue NUMERIC,
  q3_revenue NUMERIC,
  q4_revenue NUMERIC
);

-- explain_analyze_example.sql
-- Analyze a slow query to identify bottlenecks
EXPLAIN (ANALYZE, BUFFERS, FORMAT TEXT)
SELECT
  c.customer_id,
  c.name,
  COUNT(o.order_id) AS order_count,
  SUM(o.total_amount) AS lifetime_value
FROM customers c
JOIN orders o ON c.customer_id = o.customer_id
WHERE o.order_date >= '2025-01-01'
GROUP BY c.customer_id, c.name
HAVING SUM(o.total_amount) > 1000
ORDER BY lifetime_value DESC;

-- indexing_strategies.sql
-- Index on order_date: filters a small percentage of rows
CREATE INDEX idx_orders_date ON orders (order_date);

-- Composite index for queries filtering on both columns
CREATE INDEX idx_orders_customer_date
  ON orders (customer_id, order_date);

-- Covering index: includes columns needed in SELECT
-- Enables Index Only Scan (no table access)
CREATE INDEX idx_orders_covering
  ON orders (customer_id, order_date)
  INCLUDE (total_amount, status);

-- partial_index.sql
-- Only index active orders (smaller, faster index)
CREATE INDEX idx_orders_active
  ON orders (customer_id, order_date)
  WHERE status = 'active';

-- Only index recent data for dashboard queries
CREATE INDEX idx_orders_recent
  ON orders (order_date)
  WHERE order_date >= '2026-01-01';

-- anti_patterns.sql
-- BAD: function on indexed column disables the index
SELECT * FROM orders
WHERE EXTRACT(YEAR FROM order_date) = 2026;

-- GOOD: range comparison uses the index
SELECT * FROM orders
WHERE order_date >= '2026-01-01'
  AND order_date < '2027-01-01';

-- not_in_null_trap.sql
-- BAD: returns empty if any customer_id is NULL in subquery
SELECT * FROM customers
WHERE customer_id NOT IN (
  SELECT customer_id FROM orders
);

-- GOOD: NOT EXISTS handles NULLs correctly
SELECT * FROM customers c
WHERE NOT EXISTS (
  SELECT 1 FROM orders o
  WHERE o.customer_id = c.customer_id
);