.NET下文本相似度算法余弦定理和SimHash浅析及应用实例分析

                    _termWeight[i][j]=ComputeTermWeight (i, j);
            }
        }
 
        private float GetTermFrequency(int term, int doc)
        {           
            int freq=_termFreq [term][doc];
            int maxfreq=_maxTermFreq[doc];           
           
            return ( (float) freq/(float)maxfreq );
        }
 
        private float GetInverseDocumentFrequency(int term)
        {
            int df=_docFreq[term];
            return Log((float) (_numDocs) / (float) df );
        }
 
        private float ComputeTermWeight(int term, int doc)
        {
            float tf=GetTermFrequency (term, doc);
            float idf=GetInverseDocumentFrequency(term);
            return tf * idf;
        }
       
        private  float[] GetTermVector(int doc)
        {
            float[] w=new float[_numTerms] ;
            for (int i=0; i < _numTerms; i++)
                w[i]=_termWeight[i][doc];
            return w;
        }
 
        public float GetSimilarity(int doc_i, int doc_j)
        {
            float[] vector1=GetTermVector (doc_i);
            float[] vector2=GetTermVector (doc_j);
            return TermVector.ComputeCosineSimilarity(vector1, vector2);