107.Spark大型电商项目-各区域热门商品统计-使用开窗函数统计各区域的top3热门商品

本篇文章记录各区域热门商品统计-使用开窗函数统计各区域的top3热门商品。

代码

AreaTop3ProductSpark.java

private static JavaRDD<Row> getAreaTop3ProductRDD(SQLContext sqlContext){

        // 技术点：开窗函数

        // 使用开窗函数先进行一个子查询
        // 按照area进行分组，给每个分组内的数据，按照点击次数降序排序，打上一个组内的行号
        // 接着在外层查询中，过滤出各个组内的行号排名前3的数据
        // 其实就是咱们的各个区域下top3热门商品
        String sql = "SELECT " +
                    "area, " +
                    "product_id, " +
                    "click_count," +
                    "city_infos," +
                    "product_name, " +
                    "product_status " +
                    "FROM (" +
                        "SELECT " +
                            "area, " +
                            "product_id, " +
                            "click_count," +
                            "city_infos," +
                            "product_name, " +
                            "product_status," +
                            "ROW_NUMBER() OVER(PARTITION BY area ORDER BY click_count DESC) rank " +
                    "FROM tmp_area_fullprod_click_count " +
                    ") t " +
                "WHERE rank <=3";
        Dataset ds = sqlContext.sql(sql);
        return ds.javaRDD();
    }