document_summarization.py 文件源码

def textrank_text_summarizer(documents, num_sentences=2,
                             feature_type='frequency'):

    vec, dt_matrix = build_feature_matrix(norm_sentences, 
                                      feature_type='tfidf')
    similarity_matrix = (dt_matrix * dt_matrix.T)

    similarity_graph = networkx.from_scipy_sparse_matrix(similarity_matrix)
    scores = networkx.pagerank(similarity_graph)   

    ranked_sentences = sorted(((score, index) 
                                for index, score 
                                in scores.items()), 
                              reverse=True)

    top_sentence_indices = [ranked_sentences[index][1] 
                            for index in range(num_sentences)]
    top_sentence_indices.sort()

    for index in top_sentence_indices:
        print sentences[index]