Scala FPGrowth类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Scala›Scala教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Scala中org.apache.spark.mllib.fpm.FPGrowth类的典型用法代码示例。如果您正苦于以下问题：Scala FPGrowth类的具体用法？Scala FPGrowth怎么用？Scala FPGrowth使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

在下文中一共展示了FPGrowth类的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: SampleFPGrowthApp

//设置package包名称以及导入依赖的类
package com.sparksample

import org.apache.spark.mllib.fpm.FPGrowth


object SampleFPGrowthApp {
  def main(args: Array[String]) {
    val transactions = Seq(
      "r z h k p",
      "z y x w v u t s",
      "s x o n r",
      "x z y m t s q e",
      "z",
      "x z y r q t p")
      .map(_.split(" "))
    val sc = Util.sc
    val rdd = sc.parallelize(transactions, 2).cache()

    val fpg = new FPGrowth()

    val model6 = fpg
      .setMinSupport(0.2)
      .setNumPartitions(1)
      .run(rdd)

    model6.freqItemsets.collect().foreach { itemset =>
        println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
    }
  }
}

开发者ID:PacktPublishing，项目名称:Machine-Learning-with-Spark-Second-Edition，代码行数:31，代码来源:SampleFPGrowthApp.scala

示例2: SampleFPGrowthApp

//设置package包名称以及导入依赖的类
import org.apache.spark.SparkContext
import org.apache.spark.mllib.fpm.FPGrowth


object SampleFPGrowthApp {
  def main(args: Array[String]) {
    val transactions = Seq(
      "r z h k p",
      "z y x w v u t s",
      "s x o n r",
      "x z y m t s q e",
      "z",
      "x z y r q t p")
      .map(_.split(" "))
    val sc = new SparkContext("local[2]", "Chapter 5 App")
    val rdd = sc.parallelize(transactions, 2).cache()

    val fpg = new FPGrowth()

    val model = fpg
      .setMinSupport(0.2)
      .setNumPartitions(1)
      .run(rdd)

    model.freqItemsets.collect().foreach { itemset =>
        println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
    }
  }
}

开发者ID:PacktPublishing，项目名称:Machine-Learning-with-Spark-Second-Edition，代码行数:30，代码来源:SampleFPGrowthApp.scala

示例3:

//设置package包名称以及导入依赖的类
import org.apache.spark.SparkContext
import org.apache.spark.mllib.fpm.FPGrowth
import org.apache.spark.mllib.recommendation.Rating

import scala.collection.mutable.ListBuffer


    val rawRatings = rawData.map(_.split("\t").take(3))
    rawRatings.first()
    // 14/03/30 13:22:44 INFO SparkContext: Job finished: first at <console>:21, took 0.003703 s
    // res25: Array[String] = Array(196, 242, 3)

    val ratings = rawRatings.map { case Array(user, movie, rating) => Rating(user.toInt, movie.toInt, rating.toDouble) }
    val ratingsFirst = ratings.first()
    println(ratingsFirst)

    val userId = 789
    val K = 10

    val movies = sc.textFile(PATH + "/ml-100k/u.item")
    val titles = movies.map(line => line.split("\\|").take(2)).map(array => (array(0).toInt, array(1))).collectAsMap()
    titles(123)

    var eRDD = sc.emptyRDD
    var z = Seq[String]()

    val l = ListBuffer()
    val aj = new Array[String](100)
    var i = 0
    for( a <- 801 to 900) {
      val moviesForUserX = ratings.keyBy(_.user).lookup(a)
      val moviesForUserX_10 = moviesForUserX.sortBy(-_.rating).take(10)
      val moviesForUserX_10_1 = moviesForUserX_10.map(r => r.product)
      var temp = ""
      for( x <- moviesForUserX_10_1){
        temp = temp + " " + x
        println(temp)

      }

      aj(i) = temp
      i += 1
    }
    z = aj
    val transaction2 = z.map(_.split(" "))

    val rddx = sc.parallelize(transaction2, 2).cache()

    val fpg = new FPGrowth()
    val model6 = fpg
      .setMinSupport(0.1)
      .setNumPartitions(1)
      .run(rddx)

    model6.freqItemsets.collect().foreach { itemset =>
      println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
    }
    sc.stop()
  }

}

开发者ID:PacktPublishing，项目名称:Machine-Learning-with-Spark-Second-Edition，代码行数:62，代码来源:MovieLensFPGrowthApp.scala

示例4:

//设置package包名称以及导入依赖的类
package com.sparksample

import org.apache.spark.mllib.fpm.FPGrowth
import org.apache.spark.mllib.recommendation.Rating

import scala.collection.mutable.ListBuffer


    val rawRatings = rawData.map(_.split("\t").take(3))
    rawRatings.first()
    val ratings = rawRatings.map { case Array(user, movie, rating) => Rating(user.toInt, movie.toInt, rating.toDouble) }
    val ratingsFirst = ratings.first()
    println(ratingsFirst)

    val movies = Util.getMovieData()
    val titles = movies.map(line => line.split("\\|").take(2)).map(array => (array(0).toInt, array(1))).collectAsMap()
    titles(123)

    var eRDD = sc.emptyRDD
    var z = Seq[String]()

    val l = ListBuffer()
    val aj = new Array[String](400)
    var i = 0
    for( a <- 501 to 900) {
      val moviesForUserX = ratings.keyBy(_.user).lookup(a)
      val moviesForUserX_10 = moviesForUserX.sortBy(-_.rating).take(10)
      val moviesForUserX_10_1 = moviesForUserX_10.map(r => r.product)
      var temp = ""
      for( x <- moviesForUserX_10_1){
        if(temp.equals(""))
          temp = x.toString
        else {
          temp =  temp + " " + x
        }
      }

      aj(i) = temp
      i += 1
    }
    z = aj

    val transaction = z.map(_.split(" "))
    val rddx = sc.parallelize(transaction, 2).cache()

    val fpg = new FPGrowth()
    val model = fpg
      .setMinSupport(0.1)
      .setNumPartitions(1)
      .run(rddx)

    model.freqItemsets.collect().foreach { itemset =>
      println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
    }
    sc.stop()
  }

}

开发者ID:PacktPublishing，项目名称:Machine-Learning-with-Spark-Second-Edition，代码行数:59，代码来源:MovieLensFPGrowthApp.scala

示例5: FPMiningApp

//设置package包名称以及导入依赖的类
package org.apress.prospark

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.mllib.fpm.FPGrowth
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.StreamingContext

object FPMiningApp {

  def main(args: Array[String]) {
    if (args.length != 3) {
      System.err.println(
        "Usage: FPMiningApp <appname> <batchInterval> <iPath>")
      System.exit(1)
    }
    val Seq(appName, batchInterval, iPath) = args.toSeq

    val conf = new SparkConf()
      .setAppName(appName)
      .setJars(SparkContext.jarOfClass(this.getClass).toSeq)

    val ssc = new StreamingContext(conf, Seconds(batchInterval.toInt))

    val minSupport = 0.4

    ssc.textFileStream(iPath)
      .map(r => r.split(" "))
      .foreachRDD(transactionRDD => {
        val fpg = new FPGrowth()
          .setMinSupport(minSupport)
        val model = fpg.run(transactionRDD)

        model.freqItemsets
          .collect()
          .foreach(itemset => println("Items: %s, Frequency: %s".format(itemset.items.mkString(" "), itemset.freq)))
      })

    ssc.start()
    ssc.awaitTermination()
  }

}

开发者ID:ZubairNabi，项目名称:prosparkstreaming，代码行数:44，代码来源:L9-14FPMining.scala

注：本文中的org.apache.spark.mllib.fpm.FPGrowth类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。