char_generator.py 文件源码

def preprocess(self, input_file, vocab_file, tensor_file):
        with codecs.open(input_file, "r", encoding=self.encoding) as f:
            data = f.read()
        counter = collections.Counter(data)
        count_pairs = sorted(counter.items(), key=lambda x: -x[1])
        self.chars, _ = zip(*count_pairs)
        self.vocab_size = len(self.chars)
        self.vocab = dict(zip(self.chars, range(len(self.chars))))
        with open(vocab_file, 'wb') as f:
            cPickle.dump(self.chars, f)
        self.tensor = np.array(list(map(self.vocab.get, data)))
        np.save(tensor_file, self.tensor)