一、示例
— 创建测试表CREATE EXTERNAL TABLE sample_table (id INT, name STRING, value DOUBLE) USING PARQUET LOCATION 'cosn://<your_cos_bucket>/test_sampling/sample_table';INSERT INTO sample_table VALUES (1,'a',10.0),(2,'b',20.0),(3,'c',30.0),(4,'d',40.0),(5,'e',50.0), (6,'f',60.0),(7,'g',70.0),(8,'h',80.0),(9,'i',90.0),(10,'j',100.0);– 按行数采样 (支持)SELECT * FROM sample_table TABLESAMPLE (5 ROWS);– 按百分比采样 (支持)SELECT * FROM sample_table TABLESAMPLE (50 PERCENT);– 按桶采样 (支持,注意: 不指定列名 ON id)SELECT * FROM sample_table TABLESAMPLE (BUCKET 3 OUT OF 10);– 替代方案: 使用 rand() 函数采样 (支持)SELECT * FROM sample_table WHERE rand() < 0.5;