TR4KW.py 文件源码

def sort_words(vertex_source, edge_source, model, window = 2, pagerank_config = {'alpha': 0.85,}):
    """??????????????

    Keyword arguments:
    vertex_source   --  ???????????????????????????????pagerank????
    edge_source     --  ?????????????????????????????????pagerank???
    window          --  ????????window????????????
    pagerank_config --  pagerank???
    """

    #??????????
    sorted_words   = []
    word_index     = {}
    index_word     = {}
    _vertex_source = vertex_source
    _edge_source   = edge_source
    words_number   = 0
    for word_list in _vertex_source:
        for word in word_list:
            if not word in word_index:
                word_index[word] = words_number
                index_word[words_number] = word
                words_number += 1

    graph = np.zeros((words_number, words_number))

    #???
    for word_list in _edge_source:
        for w1, w2 in combine(word_list, window):
            if w1 in word_index and w2 in word_index:
                index1 = word_index[w1]
                index2 = word_index[w2]
                try:
                    similarity = model.similarity(w1,w2)
                    if similarity<0:
                        similarity = 0
                    #print similarity
                except:
                    similarity = 0
                graph[index1][index2] = similarity
                graph[index2][index1] = similarity
#                graph[index1][index2] = 1.0
#                graph[index2][index1] = 1.0

    nx_graph = nx.from_numpy_matrix(graph)

    scores = nx.pagerank(nx_graph, max_iter=100,**pagerank_config)          # this is a dict
    sorted_scores = sorted(scores.items(), key = lambda item: item[1], reverse=True)
    for index, score in sorted_scores:
        item = AttrDict(word=index_word[index], weight=score)
        sorted_words.append(item)
    return sorted_words