<!-- spark --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-core_2.10</artifactId> <version>1.6.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql_2.10</artifactId> <version>1.6.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-hive_2.10</artifactId> <version>1.6.0</version> </dependency>
public class RowNumberTopN { public static void main(String[] args) { SparkConf conf = new SparkConf().setAppName("RowNumberTopN").setMaster("local"); JavaSparkContext sc = new JavaSparkContext(conf); HiveContext hiveContext = new HiveContext(sc.sc()); hiveContext.sql("drop table if exists sales"); //创建销售表 hiveContext.sql("create table if not exists sales(product STRING,category STRING,revenue BIGINT)"); hiveContext.sql("LOAD DATA LOCAL INPATH '/user/local/spark/resources/sales.txt' INTO TABLE sales"); //进行row_number分组 DataFrame topnDF = hiveContext.sql("SELECT product,category,revenue FROM (\n" + "SELECT product,category,revenue,row_number() OVER (PARTITION BY category ORDER BY revenue DESC) rank\n" + "FROM sales\n" + ") topn_sales where rank<=3"); hiveContext.sql("drop table if exists top3_sales"); topnDF.saveAsTable("top3_sales"); sc.close(); } }