next_word.py 文件源码

def load_data():
    global N, words

    raw = list(word 
            for fileid in corpus.fileids()
            for word in corpus.words(fileid))
    words = list(token for token in RegexpTokenizer('\w+').tokenize(' '.join(raw)))[100:1000]
    tokens = set(words)
    tokens_l = list(tokens)
    N = len(tokens)
    print 'Corpus size: {} words'.format(N)

    step = 4
    data = []
    for gram in ngrams(words, step):
        w1, w2, w3, pred = gram
        V = Vol(1, 1, N, 0.0)
        V.w[tokens_l.index(w1)] = 1
        V.w[tokens_l.index(w2)] = 1
        V.w[tokens_l.index(w3)] = 1
        label = tokens_l.index(pred)
        data.append((V, label))

    return data