集合相似度Jaccard距离

1.计算方法

package main;

import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;

/**
 * 求集合相似度Jaccard距离 J(A,B) = |A∩B|/|A∪B|
 * @author Administrator
 *
 */
public class AA {

	public static void main(String[] args) {
		// TODO Auto-generated method stub
		Set<String> set = new HashSet<String>();
		set.add("1");
		set.add("2");
		set.add("3");
		set.add("4");
		
		Set<String> set1 = new HashSet<String>();
		set1.add("1");
		set1.add("3");
		set1.add("5");
		set1.add("7");

		System.out.println(operInsertct(set,set1));
		System.out.println(operUnin(set,set1));	
		
		double Jaccard = (operInsertct(set,set1).size()*1.0)/(operUnin(set,set1).size()*1.0)*100;
		
		System.out.println("集合A,B相似度为："+Jaccard+"%");
	}

	/**
     * 求多个set数组的交集
     * @param setArrays
     * @return
     */
    public static <String> Set<String> operInsertct(Set<String>... setArrays) {
        // 计数map
        Map<String, Integer> countMap = new HashMap<String, Integer>();
        for (int i = 0; i < setArrays.length; i++) {
            for (String element : setArrays[i]) {
                Integer keyCount = (Integer) countMap.get(element);
                if (keyCount == null) {
                    countMap.put(element, 1);
                } else {
                    countMap.put(element, ++keyCount);
                }
            }
        }
        //元素出现setArrays.length代表元素在交集
        Iterator<Entry<String, Integer>> iterator = countMap.entrySet().iterator();
        while (iterator.hasNext()) {
            if ((Integer) iterator.next().getValue() != setArrays.length) {
                iterator.remove();
            }
        }
        return countMap.keySet();
    }
    
    /**
     * 求多个set数组的并集
     * @param setArrays
     * @return
     */
    public static <String> Set<String> operUnin(Set<String>... setArrays) {
        // 计数map
        Map<String, Integer> countMap = new HashMap<String, Integer>();
        for (int i = 0; i < setArrays.length; i++) {
            for (String element : setArrays[i]) {
                Integer keyCount = (Integer) countMap.get(element);
                if (keyCount == null) {
                    countMap.put(element, 1);
                }
            }
        }
        return countMap.keySet();
    }
}

2.运行结果

3.借鉴文章

集合的交集运算
Minhash算法及其应用