google搜索引擎核心PageRank

google搜索引擎核心PageRank

标签(空格分隔): Spark


001.PNG-95.5kB

002.PNG-138.1kB

003.PNG-250.3kB

004.PNG-113.2kB

005.PNG-181.4kB

006.PNG-115.9kB

007.PNG-144.5kB

算法实现源码:

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples

import org.apache.spark.{SparkConf, SparkContext}

/**
 * Computes the PageRank of URLs from an input file. Input file should
 * be in format of:
 * URL         neighbor URL
 * URL         neighbor URL
 * URL         neighbor URL
 * ...
 * where URL and their neighbors are separated by space(s).
 *
 * This is an example implementation for learning how to use Spark. For more conventional use,
 * please refer to org.apache.spark.graphx.lib.PageRank
 */
object SparkPageRank {

  def showWarning() {
    System.err.println(
      """WARN: This is a naive implementation of PageRank and is given as an example!
        |Please use the PageRank implementation found in org.apache.spark.graphx.lib.PageRank
        |for more conventional use.
      """.stripMargin)
  }

  def main(args: Array[String]) {
    if (args.length < 1) {
      System.err.println("Usage: SparkPageRank <file> <iter>")
      System.exit(1)
    }

    showWarning()

    val sparkConf = new SparkConf().setAppName("PageRank")
    val iters = if (args.length > 1) args(1).toInt else 10
    val ctx = new SparkContext(sparkConf)
    val lines = ctx.textFile(args(0), 1)
    val links = lines.map{ s =>
      val parts = s.split("\\s+")
      (parts(0), parts(1))
    }.distinct().groupByKey().cache()
    var ranks = links.mapValues(v => 1.0)

    for (i <- 1 to iters) {
      val contribs = links.join(ranks).values.flatMap{ case (urls, rank) =>
        val size = urls.size
        urls.map(url => (url, rank / size))
      }
      ranks = contribs.reduceByKey(_ + _).mapValues(0.15 + 0.85 * _)
    }

    val output = ranks.collect()
    output.foreach(tup => println(tup._1 + " has rank: " + tup._2 + "."))

    ctx.stop()
  }
}
// scalastyle:on println
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

forrestxingyunfei

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值