spark 机器学习 第二版 含源码 高清版本

spark 机器学习 第二版 含源码 高清版本

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import scala.Tuple2;
import java.util.*;
import java.util.stream.Collectors;

/**
 * A simple Spark app in Java （Wordcount example）
 */
public class JavaApp {

    public static void main（String[] args） {
        JavaSparkContext sc = null;

        try {
//           ####### create spark context by starting the cluster locally using 2 CPU cores #######
            sc = new JavaSparkContext（“local[2]“ “First Spark App“）;

            JavaRDD data = sc.textFile（“data/UserPurchaseHistory.csv“）.map（s -> s.split（““））;

//           ####### let‘s count the number of purchases #######
            long numPurchases = data.count（）;

            System.out.println（“NumberPurchases : “ + numPurchases）;

            long uniqueUsers = data.map（strings -> strings[0]）.distinct（）.count（）;

//           ####### let‘s count the number of users #######
            System.out.println（“Unique users : “ + uniqueUsers）;

            Double totalRevenue = data.map（strings -> Double.parseDouble（strings[2]））.reduce（（Double v1 Double v2） -> new Double（v1.doubleValue（） + v2.doubleValue（）））;

//           ####### let‘s count the total revenue #######
            System.out.println（“Total revenue : “ + totalRevenue）;

            List> pairs = data.mapToPair（strings -> new Tuple2（strings[1] 1））.reduceByKey（（Integer i1 Integer i2） -> i1 + i2）.collect（）;

            Map sortedData = new HashMap<>（）;
            Iterator it = pairs.iterator（）;
            while （it.hasNext（）） {
                Tuple2 o = （Tuple2） it.next（）;
                sortedData.put（o._1（） o._2（））;
            }
            List sorted = sortedData.entrySet（）
                    .stream（）
                    .sorted（Comparator.comparing（（Map.Entry entry） -> entry.getValue（））.reversed（））
                    .map（Map.Entry::getKey）
                    .collect（Collectors.toList（））;
            System.out.println（“Most popular products sorted : “ + sorted）;


            String mostPopular = sorted.get（0）;
            int purchases = sortedData.get（mostPopular）;
            System.out.println（“Most popular product is : “ + mostPopular + “ with number of purchases : “ + purchases）;
        } catch （Exception e） {
            e.printStackTrace（）;
        } finally {
            sc.stop（）;
        }


    }
}

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件      29494  2016-11-14 11:18  Graphic 图\B05184_08_01.png

     文件      29503  2016-11-13 06:47  Graphic 图\B05184_08_02.png

     文件      29517  2016-11-14 11:18  Graphic 图\B05184_08_03.png

     文件      29519  2016-11-13 06:48  Graphic 图\B05184_08_04.png

     文件      29475  2016-11-14 11:18  Graphic 图\B05184_08_05.png

     文件      19647  2016-11-14 11:18  Graphic 图\B05184_08_06.png

    .......       378  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\.gitattributes

    .......       649  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\.gitignore

    .......       251  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\java-spark-app\data\UserPurchaseHistory.csv

    .......      1060  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\java-spark-app\pom.xml

    .......      2513  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\java-spark-app\src\main\java\JavaApp.java

    .......       117  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\python-spark-app\data\UserPurchaseHistory.csv

    .......      1405  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\python-spark-app\pythonapp.py

    .......       117  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\r-spark-app\data\UserPurchaseHistory.csv

    .......      1767  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\r-spark-app\r-script-01.R

    .......       537  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\README

    .......      5120  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\scala-shell-code_01.scala

    .......       144  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\scala-spark-app\build.sbt

    .......       117  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\scala-spark-app\data\UserPurchaseHistory.csv

    .......      1426  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter01\scala-spark-app\src\main\scala\ScalaApp.scala

    .......      1093  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\build.sbt

    .......       882  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\fields\ComplexNumber.scala

    .......       285  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\fields\GaloisField.scala

    .......       579  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\fields\GF2.scala

    .......       501  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\matrix\BreezeMatrix.scala

    .......       909  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\matrix\BreezeMatrixOperations.scala

    .......      1607  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\operations\common.scala

    .......       362  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\plot\BreezePlotGaussian.scala

    .......       413  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\plot\BreezePlotLine.scala

    .......       633  2017-04-28 19:15  Machine-Learning-with-Spark-Second-Edition-master 源码\Chapter02\breeze\src\main\scala\linalg\sgd\BreezeSGDVector.scala

............此处省略1092个文件信息