文本预处理
- 读入文本
- 分词
- 建立字典,将每个词映射到一个唯一的索引(index)
- 将文本从词的序列转换为索引的序列,方便输入模型
读入文本
import collections
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]
return lines
lines = read_time_machine()
print('# sentences %d' % len(lines))
分词
将一个句子划分为若干个token
def tokenize(sentences, token='word'):
"""Split sentences into word or char tokens"""
if token == 'word':
return [sentence.split(' ') for sentence in sentences]
elif token == 'char':
return [list(sentence) for sentence in sentences]
else:
print('ERROR: unkown token type '+token)
tokens = tokenize(lines)
tokens[0:2]
建立字典
class Vocab(object):
def __init__(self, tokens, min_freq=0, use_special_tokens=False):
counter = count_corpus(tokens) # :
self.token_freqs = list(counter.items())
self.idx_to_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]
return collections.Counter(tokens) # 返回一个字典,记录每个词的出现次数
# 将词转化为索引
for i in range(8, 10):
print('words:', tokens[i])
print('indices:', vocab[tokens[i]])
用现有工具包分词
NLTK
text = "Mr. Chen doesn't agree with my suggestion."
from nltk.tokenize import word_tokenize
from nltk import data
data.path.append('/home/kesci/input/nltk_data3784/nltk_data')
print(word_tokenize(text))
SPACY
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp(text)
print([token.text for token in doc])
语言模型(基于统计的语言模型)
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-JTL7CgZu-1581672419964)(https://img.vim-cn.com/74/bb98fdc35dd04377837535271dcebd321dfa19.png)]
n元语法
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-MljPKG98-1581672419965)(https://img.vim-cn.com/14/04dcd7cd184f97d2cbaed69a419d20bdd74c96.png)]
相邻采样
在相邻采样中,相邻的两个随机小批量在原始序列上的位置相毗邻
随机采样
下面的代码每次从数据里随机采样一个小批量。其中批量大小batch_size
是每个小批量的样本数,num_steps
是每个样本所包含的时间步数。 在随机采样中,每个样本是原始序列上任意截取的一段序列,相邻的两个随机小批量在原始序列上的位置不一定相毗邻。