当前位置：首页 > Java

java如何求词频

2026-03-23 06:42:31Java

求词频的方法

在Java中求词频可以通过多种方式实现，以下是几种常见的方法：

使用HashMap统计词频

HashMap是统计词频最常用的数据结构，利用键值对存储单词及其出现次数。

import java.util.HashMap;
import java.util.Map;

public class WordFrequency {
    public static Map<String, Integer> countWordFrequency(String[] words) {
        Map<String, Integer> frequencyMap = new HashMap<>();
        for (String word : words) {
            frequencyMap.put(word, frequencyMap.getOrDefault(word, 0) + 1);
        }
        return frequencyMap;
    }

    public static void main(String[] args) {
        String[] words = {"apple", "banana", "apple", "orange", "banana", "apple"};
        Map<String, Integer> frequency = countWordFrequency(words);
        System.out.println(frequency); // 输出：{orange=1, banana=2, apple=3}
    }
}

使用Stream API简化统计

Java 8及以上版本可以使用Stream API简化词频统计代码。

import java.util.Arrays;
import java.util.Map;
import java.util.function.Function;
import java.util.stream.Collectors;

public class WordFrequencyStream {
    public static void main(String[] args) {
        String[] words = {"apple", "banana", "apple", "orange", "banana", "apple"};
        Map<String, Long> frequency = Arrays.stream(words)
            .collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
        System.out.println(frequency); // 输出：{orange=1, banana=2, apple=3}
    }
}

处理文本文件中的词频

如果需要从文本文件中统计词频，可以结合文件读取和上述方法。

java如何求词频

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.Map;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;

public class FileWordFrequency {
    public static void main(String[] args) throws IOException {
        String filePath = "sample.txt";
        try (Stream<String> lines = Files.lines(Paths.get(filePath))) {
            Map<String, Long> frequency = lines
                .flatMap(line -> Arrays.stream(line.split("\\s+")))
                .collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
            System.out.println(frequency);
        }
    }
}