SparkTest

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.*;
import scala.Tuple2;

import java.util.Arrays;
import java.util.Iterator;

public class SparkTest {

    public static void main(String[] args){

        SparkConf sparkConf = new SparkConf().setAppName("AvgAgeCalculator");
        // 提交到集群
//        sparkConf.setMaster("spark://192.168.1.126:7077");
        // idea 里面运行
        sparkConf.setMaster("local[2]");
        JavaSparkContext sc = new JavaSparkContext(sparkConf);
        //读取文件
//        JavaRDD<String> dataFile = sc.textFile(args[0]);
        JavaRDD<String> dataFile = sc.textFile("/Users/zzy/Downloads/hive/teskshanda/DataFile2.txt");
        //数据分片并取第二个数

        JavaRDD<String> ageData = dataFile.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterable<String> call(String s) throws Exception {
                return Arrays.asList(s.split(" ")[1]);
            }
        });
        //求出所有年龄个数。
        long count = ageData.count();
        //转换数据类型
        JavaRDD<Integer> ageDataInt = ageData.map(new Function<String, Integer>() {
            @Override
            public Integer call(String s) throws Exception {
                return Integer.parseInt(String.valueOf(s));
            }
        });
        //求出年龄的和
        Integer totalAge = ageDataInt.reduce(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer x, Integer y) throws Exception {
                return x+y;
            }
        });
        //平均值结果为double类型
        Double avgAge = totalAge.doubleValue()/count;
        /*System.out.println(ageData.collect());
        System.out.println(count);*/
        System.out.println("Total Age:" + totalAge + ";    Number of People:" + count );
        System.out.println("Average Age is " + avgAge);

    }

}