任务

一个在线商品购买记录数据集，约40M,格式如下：

Jack,iphone cover,9,99
Jack,iphone cover,9,99
Jack,iphone cover,9,99
Jack,iphone cover,9,99

完成统计：
1.购买总次数
2.客户总个数
3.总收入
4.最畅销的商品

代码

import java.util.Collections;
import java.util.Comparator;
import java.util.List;

import org.apache.commons.collections.comparators.ComparableComparator;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.DoubleFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;

import scala.Tuple2;

/**
 * 
 * @author jinhang
 *
 */
public class JavaApp {

    public static void main(String[] args) {
        SparkConf sparkConf = new SparkConf().setAppName("ShopInfoAnalysis").setMaster("local[*]");
        JavaSparkContext sc = new JavaSparkContext(sparkConf);
        JavaRDD<String[]> data = sc.textFile("data/UserPurchaseHistory.csv").map(s -> s.split(","));
        /**
         * 统计
         */
        long numPurchases = data.count();
        long uniqueUsers = data.map(s->s[0]).distinct().count();
        double totalRevenue = data.mapToDouble(s -> Double.parseDouble(s[2])).sum();
        JavaPairRDD<String, Integer> product = data.mapToPair(s->new Tuple2(s[1],1));
        List<Tuple2<String, Integer>> pairs= product.reduceByKey((x,y)->(x+y)).sortByKey().collect();
        System.out.println(pairs);
        String mostPopular = pairs.get(pairs.size()-1)._1();
        int purchases = pairs.get(0)._2();
        System.out.println("Total purchases: " + numPurchases);
        System.out.println("Unique users: " + uniqueUsers);
        System.out.println("Total revenue: " + totalRevenue);
        System.out.println(String.format("Most popular product: %s with %d purchases",
                mostPopular, purchases));
        sc.stop();

    }

}

简单的RDD转换和执行就可以简单解决大数据的问题，java实现的代码方便和以前的hadoop代码结合执行。