Spark SQL（九）之基于用户的推荐公式

ゞ浴缸里的玫瑰 2023-01-18 09:28 79阅读 0赞

### 一、基于用户的推荐公式 ###

![20210505220901321.png][]

其中，S(u,K)表示与用户u最相似的K个用户，N(i)代表喜欢物品i的用户集合，rm表示用户v对物品i的评分。

### 二、代码 ###

public class UserCFRecommendApp {
    
        public static void main(String[]args){
    
            SparkConf sparkConf = new SparkConf();
            sparkConf.setAppName("UserCFRecommendApp");
            sparkConf.setMaster("local[*]");
            SparkSession sparkSession = SparkSession.builder().config(sparkConf).getOrCreate();
            
            String url = "jdbc:mysql://localhost:3306/spark-mysql?useUnicode=true&characterEncoding=utf8&autoReconnect=true&failOverReadOnly=false";
            String driver = "com.mysql.jdbc.Driver";
            String user = "root";
            String password = "admin";
            Dataset<Row> score = sparkSession.read()
                    .format("jdbc")
                    .option("driver", driver)
                    .option("url",url)
                    .option("dbtable","user_item")
                    .option("user",user)
                    .option("password",password)
                    .load();
    
            Dataset<Row> similar = sparkSession.read()
                    .format("jdbc")
                    .option("driver", driver)
                    .option("url",url)
                    .option("dbtable","user_similar")
                    .option("user",user)
                    .option("password",password)
                    .load();
    
            //分组 top k
    //        similar = similar.selectExpr("a_user_id", "b_user_id", "count",
    //                "ROW_NUMBER() OVER (PARTITION BY a_user_id ORDER BY count DESC) rank")
    //                .where("rank <= 10");
            //similar.show();
            Dataset<Row> result =  similar.as("us")
                     .join(score.as("s"), functions.column("us.b_user_id").$eq$eq$eq(functions.column("s.user_id")))
                    .selectExpr("us.a_user_id user_id", "s.item_id", "us.count * s.score score")
                    .groupBy("user_id", "item_id").sum("score")
                    .selectExpr("user_id", "item_id", "`sum(score)` score");
    
    
            result.show();
    //        result.write()
    //                .mode(SaveMode.Overwrite)
    //                .format("jdbc")
    //                .option("driver", driver)
    //                .option("url",url)
    //                .option("dbtable","user_item_recom")
    //                .option("user",user)
    //                .option("password",password)
    //                .save();
    
             sparkSession.stop();
        }
    }

[20210505220901321.png]: /images/20221021/81090742af564220b93750946c9cdb12.png