WGGraph.py 文件源码

def generateSimMatrix(phraseList):
    #print 'Num elements', len(phraseList), phraseList
    all_elements=[]
    #for elementlist in phraseList:
    for element in phraseList:
        if len(element.strip())==0:
            all_elements.append(' ')
        else:
            all_elements.append(element.strip())
    tfidf_vectorizer = TfidfVectorizer(min_df=0, stop_words=None)
    tfidf_matrix_train = tfidf_vectorizer.fit_transform(all_elements)  #finds the tfidf score with normalization
    cosineSimilarities=cosine_similarity(tfidf_matrix_train, tfidf_matrix_train) 
    return cosineSimilarities