prep_wikiqa_data.py 文件源码

def find_similar_words(wordvecs):
    """ Use loaded word embeddings to find out the most similar words in the
    embedded vector space.
    """
    from sklearn.metrics import pairwise_distances
    from scipy.spatial.distance import cosine
    pairwise_sim_mat = 1 - pairwise_distances(wordvecs.W[1:],
                                              metric='cosine',
                                              # metric='euclidean',
                                              )

    id2word = {}
    for key, value in wordvecs.word_idx_map.iteritems():
        assert(value not in id2word)
        id2word[value] = key
    while True:
        word = raw_input("Enter a word ('STOP' to quit): ")
        if word == 'STOP': break
        try:
            w_id = wordvecs.word_idx_map[word]
        except KeyError:
            print '%s not in the vocabulary.' % word
        sim_w_id  = pairwise_sim_mat[w_id-1].argsort()[-10:][::-1]
        for i in sim_w_id:
            print id2word[i+1],
        print ''