Spark-based movie recommendation system (recommendation system to 7)

Spark movie recommendation system based on (recommended system 1-7)
22/100
publish articles
liuge36

Part IV - Recommended system - real-time recommendations

• This module model in Section 4 was based, began to make real-time recommendations for the user, the user is most likely to recommend a favorite five movie.

  A couple of points

  1. Source data testData test set. This is inside the user, may be present in the training set, it could be a new user. So, here to do the processing.

1. SparkStreaming + kakfa
   

Coding Start ##
Step a: In streaming packet, new PopularMovies2

package com.csylh.recommend.streaming

import com.csylh.recommend.config.AppConf
import org.apache.spark.sql.SaveMode

/**
  * Description: 个性化推荐
  *
  * @Author: 留歌36
  * @Date: 2019/10/18 17:42
  */
object PopularMovies2 extends AppConf{
    def main(args: Array[String]): Unit = {
        val movieRatingCount = spark.sql("select count(*) c, movieid from trainingdata group by movieid order by c")
        // 前5部进行推荐
        val Top5Movies = movieRatingCount.limit(5)

        Top5Movies.registerTempTable("top5")

        val top5DF = spark.sql("select a.title from movies a join top5 b on a.movieid=b.movieid")

        // 把数据写入到HDFS上
        top5DF.write.mode(SaveMode.Overwrite).parquet("/tmp/top5DF")

        // 将数据从HDFS加载到Hive数据仓库中去
        spark.sql("drop table if exists top5DF")
        spark.sql("create table if not exists top5DF(title string) stored as parquet")
        spark.sql("load data inpath '/tmp/top5DF' overwrite into table top5DF")

        // 最终表里应该是5部推荐电影的名称
    }
}

Step Two: In streaming packet, new SparkDirectStreamApp

package com.csylh.recommend.streaming

import com.csylh.recommend.config.AppConf
import kafka.serializer.StringDecoder
import org.apache.spark.mllib.recommendation.MatrixFactorizationModel
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
  * Description:
  *
  * @Author: 留歌36
  * @Date: 2019/10/18 16:33
  */
object SparkDirectStreamApp extends AppConf{
    def main(args:Array[String]): Unit ={
      val ssc = new StreamingContext(sc, Seconds(5))

      val topics = "movie_topic".split(",").toSet

      val kafkaParams = Map[String, String](
        "metadata.broker.list"->"hadoop001:9093,hadoop001:9094,hadoop001:9095",
        "auto.offset.reset" -> "largest" //smallest :从头开始 largest：最新
      )
      // Direct 模式：SparkStreaming 主动去Kafka中pull拉数据
      val modelPath = "/tmp/BestModel/0.8521581387523667"
      val stream = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](ssc, kafkaParams, topics)

      def exist(u: Int): Boolean = {
        val trainingdataUserIdList = spark.sql("select distinct(userid) from trainingdata")
          .rdd
          .map(x => x.getInt(0))
          .collect()  // RDD[row] ==> RDD[Int]

        trainingdataUserIdList.contains(u)
      }

      // 为没有登录的用户推荐电影的策略：
      // 1.推荐观看人数较多的电影，采用这种策略
      // 2.推荐最新的电影
      val defaultrecresult = spark.sql("select * from top5DF").rdd.toLocalIterator

      // 创建SparkStreaming接收kafka消息队列数据的2种方式
      // 一种是Direct approache,通过SparkStreaming自己主动去Kafka消息队
      // 列中查询还没有接收进来的数据，并把他们拉pull到sparkstreaming中。

      val model = MatrixFactorizationModel.load(ssc.sparkContext, modelPath)
      val messages = stream.foreachRDD(rdd=> {

              val userIdStreamRdd = rdd.map(_._2.split("|")).map(x=>x(1)).map(_.toInt)

              val validusers = userIdStreamRdd.filter(userId => exist(userId))
              val newusers = userIdStreamRdd.filter(userId => !exist(userId))

              // 采用迭代器的方式来避开对象不能序列化的问题。
              // 通过对RDD中的每个元素实时产生推荐结果，将结果写入到redis，或者其他高速缓存中，来达到一定的实时性。
              // 2个流的处理分成2个sparkstreaming的应用来处理。
              val validusersIter = validusers.toLocalIterator
              val newusersIter = newusers.toLocalIterator

              while (validusersIter.hasNext) {
                val u= validusersIter.next
                println("userId"+u)
                val recresult = model.recommendProducts(u, 5)
                val recmoviesid = recresult.map(_.product)
                println("我为用户" + u + "【实时】推荐了以下5部电影：")
                for (i <- recmoviesid) {
                  val moviename = spark.sql(s"select title from movies where movieId=$i").first().getString(0)
                  println(moviename)
                }
              }

              while (newusersIter.hasNext) {
                println("*新用户你好*以下电影为您推荐below movies are recommended for you :")
                for (i <- defaultrecresult) {
                  println(i.getString(0))
                }
              }


     })
      ssc.start()
      ssc.awaitTermination()
    }
}

Step three: the project will be created to package uploaded to the server
mvn clean package -Dmaven.test.skip=true

Step four: write your personalized referral code execution shell script

[root@hadoop001 ml]# vim PopularMovies2.sh 
export HADOOP_CONF_DIR=/root/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop

$SPARK_HOME/bin/spark-submit \
--class com.csylh.recommend.streaming.PopularMovies2 \
--master spark://hadoop001:7077 \
--name PopularMovies2 \
--driver-memory 10g \
--executor-memory 5g \
/root/data/ml/movie-recommend-1.0.jar

Step five: Perform sh PopularMovies2.sh

make sure:

[root@hadoop001 ml]# spark-sql
19/10/20 22:59:28 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark master: local[*], Application Id: local-1571583574311
spark-sql> show tables;
default links   false
default movies  false
default ratings false
default tags    false
default testdata    false
default top5df  false
default trainingdata    false
default trainingdataasc false
default trainingdatadesc    false
Time taken: 2.232 seconds, Fetched 9 row(s)
spark-sql> select * from top5df;
Follow the Bitch (1996)
Radio Inside (1994)
Faces of Schlock (2005)
Mág (1988)
"Son of Monte Cristo
Time taken: 1.8 seconds, Fetched 5 row(s)
spark-sql> 

Step six: Re-write model real-referral code execution shell script

export HADOOP_CONF_DIR=/root/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop

$SPARK_HOME/bin/spark-submit \
--class com.csylh.recommend.streaming.SparkDirectStreamApp \
--master spark://hadoop001:7077 \
--name SparkDirectStreamApp \
--driver-memory 10g \
--executor-memory 5g \
--total-executor-cores 10 \
--jars /root/app/kafka_2.11-1.1.1/libs/kafka-clients-1.1.1.jar \
--packages "mysql:mysql-connector-java:5.1.38,org.apache.spark:spark-streaming-kafka-0-8_2.11:2.4.2" \
/root/data/ml/movie-recommend-1.0.jar

Step seven: sh SparkDirectStreamApp.sh

// ALL...

Have any questions, please leave a message with the exchange ~~
More Articles: Spark movie recommendation system based on: https: //blog.csdn.net/liuge36/column/info/29285

Part IV - Recommended system - real-time recommendations
of this module model in Section 4 was based, began to make real-time recommendations for the user, the user is most likely to recommend a favorite five movie.
Some instructions
1. The data source is the data testData test set. This is inside the user, may be present in the training set, it could be a new user. So, here to do the processing.

1. SparkStreaming + kakfa
   here Insert Picture Description

Coding Start
Step a: In streaming packet, new PopularMovies2

package com.csylh.recommend.streaming

import com.csylh.recommend.config.AppConf
import org.apache.spark.sql.SaveMode

/**

• Description: Personalized Recommendation
• @Author: stay 36 songs

• @Date: 2019/10/18 17:42
  /
  object PopularMovies2 extends AppConf{
  def main(args: Array[String]): Unit = {
  val movieRatingCount = spark.sql("select count() c, movieid from trainingdata group by movieid order by c")
  // 前5部进行推荐
  val Top5Movies = movieRatingCount.limit(5)

  Top5Movies.registerTempTable("top5")
  
  val top5DF = spark.sql("select a.title from movies a join top5 b on a.movieid=b.movieid")
  
  // 把数据写入到HDFS上
  top5DF.write.mode(SaveMode.Overwrite).parquet("/tmp/top5DF")
  
  // 将数据从HDFS加载到Hive数据仓库中去
  spark.sql("drop table if exists top5DF")
  spark.sql("create table if not exists top5DF(title string) stored as parquet")
  spark.sql("load data inpath '/tmp/top5DF' overwrite into table top5DF")
  
  // 最终表里应该是5部推荐电影的名称

  }
  }

Step Two: In streaming packet, new SparkDirectStreamApp

package com.csylh.recommend.streaming

import com.csylh.recommend.config.AppConf
import kafka.serializer.StringDecoder
import org.apache.spark.mllib.recommendation.MatrixFactorizationModel
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**

• Description:
• @Author: stay 36 songs

• @Date: 2019/10/18 16:33
  */
  object SparkDirectStreamApp extends AppConf{
  def main(args:Array[String]): Unit ={
  val ssc = new StreamingContext(sc, Seconds(5))

  val topics = "movie_topic".split(",").toSet

  kafkaParams = the Map Val [String, String] (
  "metadata.broker.list" -> "hadoop001: 9093, hadoop001: 9094, hadoop001: 9095",
  "auto.offset.reset" -> "Largest" // Smallest: from scratch began to largest: the latest
  )
  // Direct mode: SparkStreaming the initiative to pull pull data Kafka in
  Val the modelPath = "/tmp/BestModel/0.8521581387523667"
  Val Stream = KafkaUtils.createDirectStream String, String, StringDecoder, StringDecoder

  def exist(u: Int): Boolean = {
  val trainingdataUserIdList = spark.sql("select distinct(userid) from trainingdata")
  .rdd
  .map(x => x.getInt(0))
  .collect() // RDD[row] ==> RDD[Int]

  trainingdataUserIdList.contains(u)

  }

  // movies recommended for users not logged strategy:
  // 1. Recommended higher number of movies to watch, this strategy
  // 2. Recommended latest movies
  val defaultrecresult = spark.sql ( "select * from top5DF") .rdd.toLocalIterator

  // Create SparkStreaming receiving kafka message queue data in two ways
  // One is Direct approache, through their own initiative to Kafka SparkStreaming team news
  // column inquiry has not yet received incoming data, and bring them to pull in sparkstreaming.

  val model = MatrixFactorizationModel.load(ssc.sparkContext, modelPath)
  val messages = stream.foreachRDD(rdd=> {

        val userIdStreamRdd = rdd.map(_._2.split("|")).map(x=>x(1)).map(_.toInt)
  
        val validusers = userIdStreamRdd.filter(userId => exist(userId))
        val newusers = userIdStreamRdd.filter(userId => !exist(userId))
  
        // 采用迭代器的方式来避开对象不能序列化的问题。
        // 通过对RDD中的每个元素实时产生推荐结果，将结果写入到redis，或者其他高速缓存中，来达到一定的实时性。
        // 2个流的处理分成2个sparkstreaming的应用来处理。
        val validusersIter = validusers.toLocalIterator
        val newusersIter = newusers.toLocalIterator
  
        while (validusersIter.hasNext) {
          val u= validusersIter.next
          println("userId"+u)
          val recresult = model.recommendProducts(u, 5)
          val recmoviesid = recresult.map(_.product)
          println("我为用户" + u + "【实时】推荐了以下5部电影：")
          for (i <- recmoviesid) {
            val moviename = spark.sql(s"select title from movies where movieId=$i").first().getString(0)
            println(moviename)
          }
        }
  
        while (newusersIter.hasNext) {
          println("*新用户你好*以下电影为您推荐below movies are recommended for you :")
          for (i <- defaultrecresult) {
            println(i.getString(0))
          }
        }

  })
  ssc.start()
  ssc.awaitTermination()
  }
  }

Step three: the project will be created to package uploaded to the server
mvn clean package -Dmaven.test.skip = true

Step four: write your personalized referral code execution shell script

[root@hadoop001 ml]# vim PopularMovies2.sh
export HADOOP_CONF_DIR=/root/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop

$SPARK_HOME/bin/spark-submit --class com.csylh.recommend.streaming.PopularMovies2 --master spark://hadoop001:7077 --name PopularMovies2 --driver-memory 10g --executor-memory 5g /root/data/ml/movie-recommend-1.0.jar

Step five: Perform sh PopularMovies2.sh

make sure:

[root@hadoop001 ml]# spark-sql
19/10/20 22:59:28 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark master: local[*], Application Id: local-1571583574311
spark-sql> show tables;
default links false
default movies false
default ratings false
default tags false
default testdata false
default top5df false
default trainingdata false
default trainingdataasc false
default trainingdatadesc false
Time taken: 2.232 seconds, Fetched 9 row(s)
spark-sql> select * from top5df;
Follow the Bitch (1996)
Radio Inside (1994)
Faces of Schlock (2005)
Mág (1988)
"Son of Monte Cristo
Time taken: 1.8 seconds, Fetched 5 row(s)
spark-sql>

Step six: Re-write model real-referral code execution shell script

export HADOOP_CONF_DIR=/root/app/hadoop-2.6.0-cdh5.7.0/etc/hadoop

$SPARK_HOME/bin/spark-submit --class com.csylh.recommend.streaming.SparkDirectStreamApp --master spark://hadoop001:7077 --name SparkDirectStreamApp --driver-memory 10g --executor-memory 5g --total-executor-cores 10 --jars /root/app/kafka_2.11-1.1.1/libs/kafka-clients-1.1.1.jar --packages "mysql:mysql-connector-java:5.1.38,org.apache.spark:spark-streaming-kafka-0-8_2.11:2.4.2" /root/data/ml/movie-recommend-1.0.jar
步骤七：sh SparkDirectStreamApp.sh

// ALL…

Have any questions, please leave a message with the exchange ~~
More Articles: Spark movie recommendation system based on: https: //blog.csdn.net/liuge36/column/info/29285

The number 214 of words in the current row Markdown 5232 rows 1, 0HTML 4908 words of paragraph 154 of the current column
Translation