data_processor.py 文件源码

def format(self, word_seq, vocab_size, sequence_size):
        words = []
        nexts = []
        sequence_count = (len(word_seq) - 1) // sequence_size
        for i in range(sequence_count):
            start = i * sequence_size
            words.append(word_seq[start:start + sequence_size])
            next_seq = word_seq[(start + 1):(start + 1 + sequence_size)]
            next_seq_as_one_hot = to_categorical(next_seq, vocab_size)  # to one hot vector
            nexts.append(next_seq_as_one_hot)

        words = np.array(words)
        nexts = np.array(nexts)

        return words, nexts