-- Sample 10% of rows from a table
SELECT * FROM large_table TABLESAMPLE SYSTEM(10);

-- Sample approximately 1000 rows
SELECT * FROM events TABLESAMPLE SYSTEM(1000 ROWS);

-- Sample from data lake files
SELECT * FROM read_parquet('s3://datalake/**/*.parquet') TABLESAMPLE SYSTEM(5);

-- Use sampling for quick data profiling
SELECT
    region,
    COUNT(*) as sample_count,
    AVG(revenue) as avg_revenue
FROM sales_data TABLESAMPLE SYSTEM(2)
GROUP BY region;

-- Sample from joins for performance
SELECT c.name, COUNT(o.id) as order_count
FROM customers c
JOIN orders o TABLESAMPLE SYSTEM(10) ON c.id = o.customer_id
GROUP BY c.name;

-- System sampling (recommended for large tables)
SELECT * FROM huge_table TABLESAMPLE SYSTEM(1);

-- Bernoulli sampling (exact percentage)
SELECT * FROM medium_table TABLESAMPLE BERNOULLI(5);