papyrus_summary_extraction_tool.py 文件源码

def function_2(text):
    paragraphs = text.split('\n\n')
    count_vect = CountVectorizer()
    bow_matrix = count_vect.fit_transform(paragraphs)
    normalized_matrix = TfidfTransformer().fit_transform(bow_matrix)
    similarity_graph = normalized_matrix * normalized_matrix.T #term frequency/inverse doc frequency applied
    similarity_graph.toarray()
    nx_graph = nx.from_scipy_sparse_matrix(similarity_graph)
    scores = nx.pagerank(nx_graph) #TextRank applied
    ranked = sorted(((scores[i],s) for i,s in enumerate(paragraphs)), reverse=True) #Sorts all paragraphs from highest to lowest scores
    ten_percent = int(round(10.00/100.00 * len(ranked)))
    ten_percent_high_scores = ranked[0:ten_percent]
    summary = [x[1] for x in ten_percent_high_scores] #Takes top 10%, so the paragraphs with the highest scores (does not disturb the rank order)
    return "\n\n".join(summary)

#Text taken from the user's uploaded PDF or URL, cleaned and formatted.