.NET下文本相似度算法余弦定理和SimHash浅析及应用(2)

private static object AddElement(IDictionary collection, object key, object newValue)
        {
            object element=collection[key];
            collection[key]=newValue;
            return element;
        }
 
        private int GetTermIndex(string term)
        {
            object index=_wordsIndex[term];
            if (index == null) return -1;
            return (int) index;
        }
 
        private void MyInit()
        {
            _terms=GenerateTerms (_docs );
            _numTerms=_terms.Count ;
 
            _maxTermFreq=new int[_numDocs] ;
            _docFreq=new int[_numTerms] ;
            _termFreq =new int[_numTerms][] ;
            _termWeight=new float[_numTerms][] ;
 
            for(int i=0; i < _terms.Count ; i++)           
            {
                _termWeight[i]=new float[_numDocs] ;
                _termFreq[i]=new int[_numDocs] ;
 
                AddElement(_wordsIndex, _terms[i], i);           
            }
           
            GenerateTermFrequency ();
            GenerateTermWeight();           
        }
       
        private float Log(float num)
        {
            return (float) Math.Log(num) ;//log2
        }
 
        private void GenerateTermFrequency()
        {
            for(int i=0; i < _numDocs  ; i++)
            {                               
                string curDoc=_docs[i];
                IDictionary freq=GetWordFrequency(curDoc);
                IDictionaryEnumerator enums=freq.GetEnumerator() ;
                _maxTermFreq[i]=int.MinValue ;
                while (enums.MoveNext())
                {
                    string word=(string)enums.Key;
                    int wordFreq=(int)enums.Value ;
                    int termIndex=GetTermIndex(word);
 
                    _termFreq [termIndex][i]=wordFreq;
                    _docFreq[termIndex] ++;
 
                    if (wordFreq > _maxTermFreq[i]) _maxTermFreq[i]=wordFreq;                   
                }
            }
        }