余弦相似度 算法

 

import java.util.ArrayList;
import java.util.List;

public class ComputerDecision {
//List<?> vector1 ;
//List<?> vector2 ;
List<Integer> vector1 = new ArrayList<Integer>();
List<Integer> vector2 = new ArrayList<Integer>();
static List<Double> vector3 = new ArrayList<Double>();
static List<Double> vector4 = new ArrayList<Double>();

public ComputerDecision(String string1, String string2) {
//把输入字符串中多个空格变为一个
String[] vector1String = string1.trim().replaceAll("\\s+", " ").split(" ");
String[] vector2String = string2.trim().replaceAll("\\s+", " ").split(" ");

for (String string : vector1String) {
vector1.add(Integer.parseInt(string));
}
for (String string : vector2String) {
vector2.add(Integer.parseInt(string));
}
}

public static void ComputerDecisiond1(String string1, String string2) {
//把输入字符串中多个空格变为一个
String[] vector1String = string1.trim().replaceAll("\\s+", " ").split(" ");
String[] vector2String = string2.trim().replaceAll("\\s+", " ").split(" ");

for (String string : vector1String) {
vector3.add(Double.valueOf(string));
}
for (String string : vector2String) {
vector4.add(Double.valueOf(string));
}
}

// 求余弦相似度
public double sim() {
double result = 0;
result = pointMulti(vector1, vector2) / sqrtMulti(vector1, vector2);

return result;
}
public static double simd() {
double result = 0;
result = pointMultid(vector3, vector4) / sqrtMultid(vector3, vector4);

return result;
}

private double sqrtMulti(List<Integer> vector1, List<Integer> vector2) {
double result = 0;
result = squares(vector1) * squares(vector2);
result = Math.sqrt(result);
return result;
}

private static double sqrtMultid(List<Double> vector1, List<Double> vector2) {
double result = 0;
result = squaresd(vector1) * squaresd(vector2);
result = Math.sqrt(result);
return result;
}

// 求平方和
private double squares(List<Integer> vector) {
double result = 0;
for (Integer integer : vector) {
result += integer * integer;
}
return result;
}
private static double squaresd(List<Double> vector) {
double result = 0;
for (Double integerd : vector) {
result += integerd * integerd;
}
return result;
}

// 点乘法
private double pointMulti(List<Integer> vector1, List<Integer> vector2) {
double result = 0;
for (int i = 0; i < vector1.size(); i++) {
result += vector1.get(i) * vector2.get(i);
}
return result;
}
private static double pointMultid(List<Double> vector1, List<Double> vector2) {
double result = 0;
for (int i = 0; i < vector1.size(); i++) {
result += vector1.get(i) * vector2.get(i);
}
return result;
}
public void ComputerDecisiond(String string1, String string2) {
//把输入字符串中多个空格变为一个
String[] vector1String = string1.trim().replaceAll("\\s+", " ").split(" ");
String[] vector2String = string2.trim().replaceAll("\\s+", " ").split(" ");

for (String string : vector1String) {
vector3.add( Double.valueOf(string.toString()));
}
for (String string : vector2String) {
vector4.add(Double.valueOf(string.toString()));
}
}
public static void main(String[] args) {

String string = "1 0 1 1 1 1 1 1 0 0 1 0 1 0 0 0 1 1 1 0 0 0 1";
String string2 ="1 0 1 1 1 1 1 1 0 1 0 0 0 1 0 0 1 1 1 0 0 0 1";
//String string3 = "5 7 9";
//String string4 = "5 9 9";

String string3 = "2.5 5.5 9.1 12.1 ";
String string4 = "1.5 5.4 9.0 12.2 ";
//ComputerDecision computerDecition = new ComputerDecisiond(string3,
// string4);
//System.out.println(computerDecition.sim());
ComputerDecisiond1(string3,
string4);
System.out.println(simd());

}
}

 

 

 

==========================================================

字符串

 

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

public class Cossimilar
{
/*
* 计算两个字符串(英文字符)的相似度，简单的余弦计算，未添权重
*/
public static double getSimilarDegree(String str1, String str2)
{
//创建向量空间模型，使用map实现，主键为词项，值为长度为2的数组，存放着对应词项在字符串中的出现次数
//Map<String, int[]> vectorSpace = new LinkedHashMap<String, int[]>();
Map<String, int[]> vectorSpace = new HashMap<String, int[]>();
int[] itemCountArray = null;//为了避免频繁产生局部变量，所以将itemCountArray声明在此

//以空格为分隔符，分解字符串
String strArray[] = str1.split(" ");
for(int i=0; i<strArray.length; ++i)
{
if(vectorSpace.containsKey(strArray[i]))
++(vectorSpace.get(strArray[i])[0]);
else
{
itemCountArray = new int[2];
itemCountArray[0] = 1;
itemCountArray[1] = 0;
vectorSpace.put(strArray[i], itemCountArray);
}
}

strArray = str2.split(" ");
for(int i=0; i<strArray.length; ++i)
{
if(vectorSpace.containsKey(strArray[i]))
++(vectorSpace.get(strArray[i])[1]);
else
{
itemCountArray = new int[2];
itemCountArray[0] = 0;
itemCountArray[1] = 1;
vectorSpace.put(strArray[i], itemCountArray);
}
}

//计算相似度
double vector1Modulo = 0.00;//向量1的模
double vector2Modulo = 0.00;//向量2的模
double vectorProduct = 0.00; //向量积
Iterator iter = vectorSpace.entrySet().iterator();

while(iter.hasNext())
{
Map.Entry entry = (Map.Entry)iter.next();
itemCountArray = (int[])entry.getValue();

vector1Modulo += itemCountArray[0]*itemCountArray[0];
vector2Modulo += itemCountArray[1]*itemCountArray[1];

vectorProduct += itemCountArray[0]*itemCountArray[1];
}

vector1Modulo = Math.sqrt(vector1Modulo);
vector2Modulo = Math.sqrt(vector2Modulo);

//返回相似度
return (vectorProduct/(vector1Modulo*vector2Modulo));
}

/*
*
*/
public static void mainxx(String args[])
{
String str1 = "gold silver truck";
String str2 = "Shipment of gold damaged in a fire";
String str3 = "Delivery of silver arrived in a silver truck";
String str4 = "Shipment of gold arrived in a truck";
String str5 = "gold gold gold gold gold gold";
String str6 = "gold gold gold gold gold dd";

System.out.println(Cossimilar.getSimilarDegree(str1, str2));
System.out.println(Cossimilar.getSimilarDegree(str1, str3));
System.out.println(Cossimilar.getSimilarDegree(str1, str4));
System.out.println(Cossimilar.getSimilarDegree(str1, str5));
System.out.println(Cossimilar.getSimilarDegree(str5, str6));
System.out.println(Cossimilar.getSimilarDegree(str6, str6));
}
}