如何使用SQL进行数据分析

-- 查看数据全貌
SELECT * FROM table_name LIMIT 10;

-- 筛选特定列和条件
SELECT column1, column2 
FROM table_name 
WHERE condition (如: date > '2023-01-01');

-- 常用聚合函数
SELECT 
    COUNT(*) AS total_rows,  -- 计数
    AVG(salary) AS avg_salary, -- 平均值
    SUM(sales) AS total_sales, -- 求和
    MAX(price) AS max_price, -- 最大值
    MIN(temperature) AS min_temp -- 最小值
FROM employees;

-- 按分组统计
SELECT department, COUNT(*) AS employee_count 
FROM employees 
GROUP BY department 
HAVING COUNT(*) > 10; -- 筛选分组结果

-- 内连接（匹配关联数据）
SELECT o.order_id, c.customer_name 
FROM orders o
INNER JOIN customers c ON o.customer_id = c.id;

-- 左连接（保留左表所有数据）
SELECT e.name, d.department_name 
FROM employees e
LEFT JOIN departments d ON e.dept_id = d.id;

-- 按销售额降序排序
SELECT product_name, sales 
FROM products 
ORDER BY sales DESC;

-- 去重统计
SELECT DISTINCT country FROM customers;

-- 子查询筛选
SELECT name, salary 
FROM employees 
WHERE salary > (SELECT AVG(salary) FROM employees);

-- 使用 CTE (公共表表达式)
WITH top_products AS (
    SELECT product_id, SUM(sales) AS total 
    FROM sales 
    GROUP BY product_id 
    ORDER BY total DESC LIMIT 10
)
SELECT * FROM top_products;

-- 计算排名
SELECT 
    name, salary,
    RANK() OVER (ORDER BY salary DESC) AS salary_rank,
    AVG(salary) OVER (PARTITION BY department) AS dept_avg_salary
FROM employees;

-- 按月份统计销售额
SELECT 
    DATE_TRUNC('month', order_date) AS month,
    SUM(amount) AS monthly_sales
FROM orders 
GROUP BY month 
ORDER BY month;

-- 处理空值
SELECT COALESCE(salary, 0) AS adjusted_salary FROM employees;

-- 条件判断
SELECT 
    CASE 
        WHEN age < 18 THEN 'Underage'
        ELSE 'Adult' 
    END AS age_group
FROM users;

-- 字符串处理
SELECT SUBSTRING(email, POSITION('@' IN email)+1) AS email_domain 
FROM users;

SELECT 
    department,
    gender,
    AVG(salary) AS avg_salary,
    COUNT(*) AS employee_count
FROM employees
GROUP BY department, gender
ORDER BY department, gender;

加载更多