文本预处理(pytorth实现)：

1.读入文本

import re


def read_time_machine():
    with open('/home/kesci/input/timemachine7163/timemachine.txt', 'r') as f:
        lines = [re.sub('[^a-z]+', ' ', line.strip().lower()) for line in f]
        # strip去掉了句头，句尾的空格。low将大写变为小写
        #re.sub 正则表达式：非英文字符构成空格
    return lines


lines = read_time_machine()
print('# sentences %d' % len(lines))

2.分词

 不采取传统的分词方法，因为会丢语意信息，因此直接使用现有的工具进行很好的分词。比如

spaCy和 NLTK:

import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(text)
print([token.text for token in doc])

from nltk.tokenize import word_tokenize
from nltk import data
data.path.append('/home/kesci/input/nltk_data3784/nltk_data')
print(word_tokenize(text))

3.建立字典

  为了方便模型处理，我们需要将字符串转换为数字。因此我们需要先构建一个字典（vocabulary），将每个词映射到一个唯一的索引编号。

class Vocab(object):
    #定义有一个类，提供词的索引编号。
    def __init__(self, tokens, min_freq=0, use_special_tokens=False):
        counter = count_corpus(tokens)  # :去重， 统计词频
        self.token_freqs = list(counter.items())
        self.idx_to_token = []#控制列表，记录需要维护的token
        if use_special_tokens:
            # padding, begin of sentence, end of sentence, unknown
            self.pad, self.bos, self.eos, self.unk = (0, 1, 2, 3)
            self.idx_to_token += ['', '', '', '']
        else:
            self.unk = 0
            self.idx_to_token += ['']
        self.idx_to_token += [token for token, freq in self.token_freqs
                        if freq >= min_freq and token not in self.idx_to_token]
        self.token_to_idx = dict()
        for idx, token in enumerate(self.idx_to_token):
            self.token_to_idx[token] = idx

    def __len__(self):
        return len(self.idx_to_token)

    def __getitem__(self, tokens):
        if not isinstance(tokens, (list, tuple)):
            return self.token_to_idx.get(tokens, self.unk)
        return [self.__getitem__(token) for token in tokens]

    def to_tokens(self, indices):
        if not isinstance(indices, (list, tuple)):
            return self.idx_to_token[indices]
        return [self.idx_to_token[index] for index in indices]

def count_corpus(sentences):
    tokens = [tk for st in sentences for tk in st]#展平得到一维的列表
    return collections.Counter(tokens)  # 返回一个字典，记录每个词的出现次数

4.将词转换为索引

for i in range(8, 10):
    print('words:', tokens[i])
    print('indices:', vocab[tokens[i]])