向量空间模型文档相似度计算实现(C#)

读者可以根据自己的需要进行加壳或改写,本文权当抛砖引玉。笔者加的壳在:http://download.csdn.net/source/1143450 VSM模型介绍:http://blog.csdn.net/Felomeng/archive/2009/03/25/4024078.aspx using System;using System.Collections.G
摘要由CSDN通过智能技术生成

读者可以根据自己的需要进行加壳或改写,本文权当抛砖引玉。

笔者加的壳在:

http://download.csdn.net/source/1143450

 

VSM模型介绍:

http://blog.csdn.net/Felomeng/archive/2009/03/25/4024078.aspx

 

using System;

using System.Collections.Generic;

using System.Linq;

using System.Text;

using System.Text.RegularExpressions;

 

namespace Felomeng.VSMSimilarity

{

    class SVMModle

    {

        /// <summary>

        /// 降维词表

        /// </summary>

        private List<string> reducingKeys = new List<string>();

        /// <summary>

        /// 构造函数:使用降维表

        /// </summary>

        /// <param name="reducingKeys">降维词表</param>

        public SVMModle(List<string> reducingKeys)

        {

            this.reducingKeys = reducingKeys;

        }

  • 2
    点赞
  • 15
    收藏
    觉得还不错? 一键收藏
  • 10
    评论
namespace ServiceRanking { /// <summary> /// Summary description for TF_IDFLib. /// </summary> public class TFIDFMeasure { private string[] _docs; private string[][] _ngramDoc; private int _numDocs=0; private int _numTerms=0; private ArrayList _terms; private int[][] _termFreq; private float[][] _termWeight; private int[] _maxTermFreq; private int[] _docFreq; public class TermVector { public static float ComputeCosineSimilarity(float[] vector1, float[] vector2) { if (vector1.Length != vector2.Length) throw new Exception("DIFER LENGTH"); float denom=(VectorLength(vector1) * VectorLength(vector2)); if (denom == 0F) return 0F; else return (InnerProduct(vector1, vector2) / denom); } public static float InnerProduct(float[] vector1, float[] vector2) { if (vector1.Length != vector2.Length) throw new Exception("DIFFER LENGTH ARE NOT ALLOWED"); float result=0F; for (int i=0; i < vector1.Length; i++) result += vector1[i] * vector2[i]; return result; } public static float VectorLength(float[] vector) { float sum=0.0F; for (int i=0; i < vector.Length; i++) sum=sum + (vector[i] * vector[i]); return (float)Math.Sqrt(sum); } } private IDictionary _wordsIndex=new Hashtable() ; public TFIDFMeasure(string[] documents) { _docs=documents; _numDocs=documents.Length ; MyInit(); } private void GeneratNgramText() { } private ArrayList GenerateTerms(string[] docs) { ArrayList uniques=new ArrayList() ; _ngramDoc=new string[_numDocs][] ; for (int i=0; i < docs.Length ; i++) { Tokeniser tokenizer=new Tokeniser() ; string[] words=tokenizer.Partition(docs[i]); for (int j=0; j < words.Length ; j++) if (!uniques.Contains(words[j]) ) uniques.Add(words[j]) ; } return uniques; } private static object
评论 10
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值