import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Comparator;
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.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;
public class Demo {
public static void main(String[] args) {
String filename = "/home/iiip/PycharmProjects/InterestModel/data/sample/机器学习/D0002033.txt";
Demo demo = new Demo();
demo.CountWord(filename);
}
public List<Map.Entry<String, Integer>> CountWord(String filename) {
SparkConf conf = new SparkConf();
conf.set("Spark.testing.memory", "2147480000");
JavaSparkContext sc = new JavaSparkContext("local[*]", "Spark", conf);
JavaRDD<String> lines = sc.textFile(filename); // 读取文件的每一行
JavaRDD<String> words = lines.flatMap(new FlatWord()); // 从每一个行中读取单个的词
JavaPairRDD<String, Integer> wordsPair = words.mapToPair(new MapOne()); // 将词语做成<key,Value>键值对
JavaPairRDD<String , Integer> wordWithNum = wordsPair.reduceByKey(new WordCount()); // 对<key,Value>做一个Reduce操作
List<Tuple2<String, Integer>> result = wordWithNum.collect(); // 获取结果
Map<String, Integer> map = new HashMap<String , Integer> ();
for(Tuple2<String , Integer> tuple : result){
map.put(tuple._1(), tuple._2());
}
//根据结果的键值对, 按值排序
List<Map.Entry<String, Integer>> sortedWord = new ArrayList<Map.Entry<String, Integer>>(map.entrySet());
Collections.sort(sortedWord, new Comparator<Map.Entry<String, Integer>>(){
public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2){
return (o2.getValue() - o1.getValue());
}
});
for(Map.Entry<String, Integer> word : sortedWord){
System.out.println(word.getKey() + " " + word.getValue());
}
return sortedWord;
}
static class FlatWord implements FlatMapFunction<String, String>{
// 将每个单词映射成为单个元素
@Override
public Iterable<String> call(String sentence) throws Exception {
String[] words = sentence.split(" ");
return Arrays.asList(words);
}
}
static class MapOne implements PairFunction<String, String, Integer>{
@Override
public Tuple2<String, Integer> call(String word){
return new Tuple2<String, Integer>(word, 1);
}
}
static class WordCount implements Function2<Integer, Integer , Integer>{
@Override
public Integer call(Integer i1, Integer i2){
return i1 + i2;
}
}
}
利用Java的Spark做单词统计并排序
最新推荐文章于 2023-10-14 20:10:26 发布