spark数据如下：答案仅供参考

package homeworkRDD;
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 scala.Tuple2;
public class countstudent {
  public static void main(String[] args) {
  // TODO Auto-generated method stub
  SparkConf sparkConf = new SparkConf().setAppName("PeopleInfoCalculator").setMaster("local");
    JavaSparkContext sc = new JavaSparkContext(sparkConf);
    JavaRDD<String> dataFile = sc.textFile
      ("file:///home/gyq/下载/spark-2.3.2-bin-hadoop2.7/data/countdata.txt");
    JavaRDD<String> data=dataFile.filter(f->!f.contains("成绩"));
    JavaRDD<String> jj=data.map(f->f.split(" ")[1]).distinct();
   long a=jj.count();//1
   System.out.println("参加考试的人数有： "+a);
   JavaRDD<String> rdd1=data.map(f->f.split(" ")[1]+" "+f.split(" ")[2]);
   JavaRDD<String> rdd2=rdd1.filter(f->Integer.valueOf(f.split(" ")[1])<20);
   long b=rdd2.distinct().count();//2
   System.out.println("小于20岁的人数有： "+b);
   JavaRDD<String> jj1=data.map(f->f.split(" ")[1]+" "+f.split(" ")[3]);
   JavaRDD<String> rdd3=jj1.filter(f->f.contains("男")).distinct();
   long c=rdd3.count();//3
   System.out.println("男生的人数有： "+c);
   JavaRDD<String> jj2=data.map(f->f.split(" ")[0]+" "+f.split(" ")[1]);
   JavaRDD<String> rdd4=jj2.filter(f->f.contains("13"));
   long d=rdd4.distinct().count();//4
   System.out.println("13班的人数有： "+d);
   JavaRDD<String> rdd5=data.filter(f->f.contains("chinese"));
   JavaRDD<Integer> rdd6=rdd5.map(f->Integer.valueOf(f.split(" ")[5]));
  long ff=rdd6.count();
   double g=rdd6.reduce((x,y)->x+y);
   double scorechinese=g/ff;
  System.out.println("语文平均成绩是："+scorechinese);//5
   JavaRDD<String> rdd7=data.filter(f->f.contains("12")&&f.contains("女"));
   JavaRDD<Integer> rdd8=rdd7.map(f->Integer.valueOf(f.split(" ")[5]));
   long ff1=rdd8.count();//
   double g1=rdd8.reduce((x,y)->x+y);
   double score12women=g1/ff1;
 System.out.println("12班女生平均成绩"+score12women);//6
 JavaRDD<String> rdd9=data.filter(f->f.contains("13")&&f.contains("math"));
 JavaRDD<Integer> rdd10=rdd9.map(f->Integer.valueOf(f.split(" ")[5]));
 JavaRDD<Integer> rdd11=rdd10.sortBy(f->{return f;},false,1);
 double gg=rdd11.first();
System.out.println("13班数学成绩最高是"+gg);//7
 JavaRDD<String> rdd12=data.filter(f->f.contains("12")&&f.contains("女"));
 JavaRDD<Integer> rdd13=rdd12.map(f->Integer.valueOf(f.split(" ")[5]));
 JavaPairRDD<String,Integer> rdd14=rdd12.mapToPair(f->{
  return new Tuple2<String,Integer>
  (f.split(" ")[1],Integer.valueOf(f.split(" ")[5]));
 });
 JavaPairRDD<String,Integer> rdd15=rdd14.reduceByKey((x,y)->x+y);
 JavaPairRDD<String,Integer> rdd16=rdd15.filter(f->f._2>150);
 long count=rdd16.count();
 System.out.println("总成绩>150有"+count+"人");//8
  sc.stop();
}
}