MySQL窗口函数 OVER()全解析

窗口函数([参数]) OVER (
  [PARTITION BY <分组列>] 
  [ORDER BY <排序列 ASC/DESC>]
  [ROWS BETWEEN 开始行 AND 结束行]
)

-- 创建测试数据
CREATE TABLE sales (
    id INT PRIMARY KEY AUTO_INCREMENT,
    salesperson VARCHAR(50),
    region VARCHAR(50),
    sale_date DATE,
    amount DECIMAL(10, 2)
);
INSERT INTO sales (salesperson, region, sale_date, amount) VALUES
('张三', '北京', '2024-01-01', 1000.00),
('张三', '北京', '2024-01-02', 1500.00),
('李四', '上海', '2024-01-01', 2000.00),
('李四', '上海', '2024-01-02', 2500.00),
('王五', '北京', '2024-01-01', 1200.00),
('王五', '北京', '2024-01-03', 1800.00),
('赵六', '广州', '2024-01-02', 2200.00);
-- 按销售员分区计算
SELECT 
    salesperson,
    sale_date,
    amount,
    -- 每个销售员的销售总额
    SUM(amount) OVER (PARTITION BY salesperson) AS total_by_person,
    -- 每个地区的销售总额
    SUM(amount) OVER (PARTITION BY region) AS total_by_region,
    -- 不分区（全局总额）
    SUM(amount) OVER () AS grand_total
FROM sales
ORDER BY salesperson, sale_date;

SELECT 
    salesperson,
    sale_date,
    amount,
    -- 按金额排序（分区内）
    ROW_NUMBER() OVER (PARTITION BY salesperson ORDER BY amount DESC) AS rn,
    -- 累计金额（分区内按日期排序）
    SUM(amount) OVER (PARTITION BY salesperson ORDER BY sale_date) AS running_total,
    -- 移动平均值（最近3行的平均值）
    AVG(amount) OVER (PARTITION BY salesperson ORDER BY sale_date 
         ROWS BETWEEN 2 PRECEDING AND CURRENT ROW) AS moving_avg_3
FROM sales
ORDER BY salesperson, sale_date;

-- 各种窗口帧的示例
SELECT 
    salesperson,
    sale_date,
    amount,
    -- 默认：分区内所有行
    SUM(amount) OVER (PARTITION BY salesperson) AS total_all,
    -- ROWS模式：物理行
    SUM(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS cumulative_rows,
    -- RANGE模式：逻辑值范围（相同值的行视为同一帧）
    SUM(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS cumulative_range,
    -- 滑动窗口：当前行及前2行
    SUM(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        ROWS BETWEEN 2 PRECEDING AND CURRENT ROW
    ) AS sum_last_3,
    -- 前后各一行
    SUM(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING
    ) AS sum_neighbors
FROM sales
ORDER BY salesperson, sale_date;

-- 创建测试数据
CREATE TABLE employees (
    id INT PRIMARY KEY AUTO_INCREMENT,
    name VARCHAR(50),
    department VARCHAR(50),
    salary DECIMAL(10, 2)
);
INSERT INTO employees (name, department, salary) VALUES
('张三', '技术部', 8000.00),
('李四', '技术部', 9000.00),
('王五', '技术部', 9500.00),
('赵六', '技术部', 9000.00),
('钱七', '销售部', 7000.00),
('孙八', '销售部', 8500.00),
('周九', '销售部', 8500.00),
('吴十', '销售部', 7500.00);
-- 1. ROW_NUMBER()：连续不重复的序号
SELECT 
    name,
    department,
    salary,
    ROW_NUMBER() OVER (PARTITION BY department ORDER BY salary DESC) AS row_num
FROM employees;
-- 2. RANK()：有间隔的排名（相同值排名相同，下一个排名跳跃）
SELECT 
    name,
    department,
    salary,
    RANK() OVER (PARTITION BY department ORDER BY salary DESC) AS rank_num
FROM employees;
-- 3. DENSE_RANK()：无间隔的排名（相同值排名相同，下一个排名连续）
SELECT 
    name,
    department,
    salary,
    DENSE_RANK() OVER (PARTITION BY department ORDER BY salary DESC) AS dense_rank_num
FROM employees;
-- 4. NTILE(n)：将数据分为n组
SELECT 
    name,
    department,
    salary,
    NTILE(4) OVER (PARTITION BY department ORDER BY salary DESC) AS quartile
FROM employees;

-- 5. PERCENT_RANK()：百分比排名 (rank - 1) / (total_rows - 1)
SELECT 
    name,
    department,
    salary,
    RANK() OVER (PARTITION BY department ORDER BY salary) AS rank_num,
    PERCENT_RANK() OVER (PARTITION BY department ORDER BY salary) AS percent_rank
FROM employees;
-- 6. CUME_DIST()：累计分布（小于等于当前值的行数 / 总行数）
SELECT 
    name,
    department,
    salary,
    CUME_DIST() OVER (PARTITION BY department ORDER BY salary) AS cume_dist
FROM employees;
-- 7. PERCENTILE_CONT()：连续百分位数（需要MySQL 8.0.2+）
SELECT 
    department,
    PERCENTILE_CONT(0.5) WITHIN GROUP (ORDER BY salary) 
        OVER (PARTITION BY department) AS median_salary
FROM employees
GROUP BY department, salary;
-- 8. PERCENTILE_DISC()：离散百分位数
SELECT 
    department,
    PERCENTILE_DISC(0.5) WITHIN GROUP (ORDER BY salary) 
        OVER (PARTITION BY department) AS median_salary
FROM employees
GROUP BY department, salary;

-- 9. LAG(column, n, default)：获取前n行的值
SELECT 
    name,
    department,
    salary,
    LAG(salary, 1, 0) OVER (PARTITION BY department ORDER BY salary) AS prev_salary,
    salary - LAG(salary, 1, 0) OVER (PARTITION BY department ORDER BY salary) AS salary_diff
FROM employees;
-- 10. LEAD(column, n, default)：获取后n行的值
SELECT 
    name,
    department,
    sale_date,
    amount,
    LEAD(amount, 1, 0) OVER (PARTITION BY salesperson ORDER BY sale_date) AS next_amount,
    LEAD(sale_date, 1, NULL) OVER (PARTITION BY salesperson ORDER BY sale_date) AS next_date
FROM sales;
-- 11. FIRST_VALUE(column)：窗口内第一个值
SELECT 
    name,
    department,
    salary,
    FIRST_VALUE(salary) OVER (
        PARTITION BY department 
        ORDER BY salary 
        ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
    ) AS lowest_salary,
    salary - FIRST_VALUE(salary) OVER (
        PARTITION BY department 
        ORDER BY salary 
        ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
    ) AS diff_from_lowest
FROM employees;
-- 12. LAST_VALUE(column)：窗口内最后一个值（注意默认窗口帧！）
SELECT 
    name,
    department,
    salary,
    -- 错误用法：默认窗口帧是 RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    LAST_VALUE(salary) OVER (PARTITION BY department ORDER BY salary) AS wrong_last_value,
    -- 正确用法：指定完整的窗口帧
    LAST_VALUE(salary) OVER (
        PARTITION BY department 
        ORDER BY salary 
        ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
    ) AS correct_last_value,
    -- 或者使用NTH_VALUE
    NTH_VALUE(salary, 1) OVER (
        PARTITION BY department 
        ORDER BY salary 
        ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
    ) AS first_salary,
    NTH_VALUE(salary, 2) OVER (
        PARTITION BY department 
        ORDER BY salary 
        ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING
    ) AS second_salary
FROM employees;

-- 所有聚合函数都可以作为窗口函数使用
SELECT 
    salesperson,
    region,
    sale_date,
    amount,
    -- 聚合函数
    COUNT(*) OVER (PARTITION BY salesperson) AS total_transactions,
    SUM(amount) OVER (PARTITION BY salesperson) AS total_amount,
    AVG(amount) OVER (PARTITION BY salesperson) AS avg_amount,
    MAX(amount) OVER (PARTITION BY salesperson) AS max_amount,
    MIN(amount) OVER (PARTITION BY salesperson) AS min_amount,
    -- 标准差和方差（MySQL 8.0+）
    STDDEV(amount) OVER (PARTITION BY salesperson) AS std_amount,
    VARIANCE(amount) OVER (PARTITION BY salesperson) AS var_amount,
    -- 累计聚合
    SUM(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS running_total,
    -- 移动平均
    AVG(amount) OVER (
        PARTITION BY salesperson 
        ORDER BY sale_date
        ROWS BETWEEN 2 PRECEDING AND CURRENT ROW
    ) AS moving_avg_3,
    -- 百分比
    amount * 100.0 / SUM(amount) OVER (PARTITION BY salesperson) AS percentage
FROM sales
ORDER BY salesperson, sale_date;