spark mllib推荐算法使用

最新推荐文章于 2024-01-08 16:43:35 发布

weixin_33842304

最新推荐文章于 2024-01-08 16:43:35 发布

阅读量301

点赞数 1

文章标签：大数据开发工具数据结构与算法

原文链接：https://my.oschina.net/hehongbo/blog/1545039

版权

2019独角兽企业重金招聘Python工程师标准>>>

一、pom.xml

<!-- 机器学习包 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.10</artifactId>
            <version>${spark.version}</version>
        </dependency>

二、api使用

package cn.hhb.spark.mllib

import org.apache.spark.SparkConf
/**
  *向用户推荐商品
  */
import org.apache.spark.mllib.recommendation.{ALS, Rating}
import org.apache.spark.{SparkConf, SparkContext}
// $example off$

object RecommendationExample2 {
  def main(args: Array[String]) {


    var conf = new SparkConf()
      .setAppName("RecommendationExample2")
      .setMaster("local[4]")
      .set("spark.testing.memory", "2147480000")

    val sc = new SparkContext(conf)
    val data = sc.textFile("c://test.data")

    //变换成rationg(评分)对象
    val ratings = data.map(_.split(',') match { case Array(user, item, rate) =>
      Rating(user.toInt, item.toInt, rate.toDouble)
    })

    //发生购买行为(评分)数据
    val realData = ratings.map( t=>(t.user,t.product) )

    // Build the recommendation model using ALS
    val rank = 10
    val numIterations = 10

    //模型,举证分解模型
    val model = ALS.train(ratings, rank, numIterations, 0.01)

    val usersProducts = sc.makeRDD(Array((1,1), (2,1)))

    //笛卡尔积
//    val allUsers = sc.makeRDD(Array(1,2,3,4))
//    val allProduct = sc.makeRDD(Array(1,2,3,4))
//    val userProducts = allUsers.cartesian(allProduct)
//    val unbuy = userProducts.subtract(realData)
//    unbuy.collect().foreach(println)


    //预测评分.
//    val predictions = model.predict(unbuy)
    val predictions = model.predict(usersProducts)

    predictions.collect().foreach(println)

  }

}

转载于:https://my.oschina.net/hehongbo/blog/1545039