文本预处理
步骤：
1.读入文本
2.分词
3.建立字典，将每个词映射到一个唯一的索引（index）
4.将文本从词的序列转换为索引的序列，方便输入模型
import collections
import re
##导入文本
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))
# sentences 3221
#分词
#中文用jieba分词
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
#用Time Machine作为语料构建字典
vocab = Vocab(tokens)
print(list(vocab.token_to_idx.items())[0:10])
#将词转换为索引
for i in range(8, 10):
print('words:', tokens[I])
print('indices:', vocab[tokens[I]])
#用现有工具进行分词
text = "Mr. Chen doesn't agree with my suggestion."
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))
语言模型
一段自然语言文本可以看作是一个离散时间序列，给定一个长度为的词的序列，语言模型的目标就是评估该序列是否合理，即计算该序列的概率。语言模型的参数就是词的概率以及给定前几个词情况下的条件概率。
语言模型
n元语法
序列长度增加，计算和存储多个词共同出现的概率的复杂度会呈指数级增加。n元语法通过马尔可夫假设简化模型，马尔科夫假设是指一个词的出现只与前面n个词相关，即n阶马尔可夫链（Markov chain of order ），也叫n元语法。
马尔可夫链
缺陷：
1.当n较小时，n元语法往往不准确。
2.参数空间过大
3.数据稀疏
代码：
with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
corpus_chars = f.read()
print(len(corpus_chars))
print(corpus_chars[: 40])
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[: 10000]
idx_to_char = list(set(corpus_chars)) # 去重，得到索引到字符的映射
char_to_idx = {char: i for i, char in enumerate(idx_to_char)} # 字符到索引的映射
vocab_size = len(char_to_idx)
print(vocab_size)
corpus_indices = [char_to_idx[char] for char in corpus_chars] # 将每个字符转化为索引，得到一个索引的序列
sample = corpus_indices[: 20]
print('chars:', ''.join([idx_to_char[idx] for idx in sample]))
print('indices:', sample)
def load_data_jay_lyrics():
with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
corpus_chars = f.read()
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[0:10000]
idx_to_char = list(set(corpus_chars))
char_to_idx = dict([(char, i) for i, char in enumerate(idx_to_char)])
vocab_size = len(char_to_idx)
corpus_indices = [char_to_idx[char] for char in corpus_chars]
return corpus_indices, char_to_idx, idx_to_char, vocab_size
import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
# 减1是因为对于长度为n的序列，X最多只有包含其中的前n - 1个字符
num_examples = (len(corpus_indices) - 1) // num_steps # 下取整，得到不重叠情况下的样本个数
example_indices = [i * num_steps for i in range(num_examples)] # 每个样本的第一个字符在corpus_indices中的下标
random.shuffle(example_indices)
def _data(i):
# 返回从i开始的长为num_steps的序列
return corpus_indices[i: i + num_steps]
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
for i in range(0, num_examples, batch_size):
# 每次选出batch_size个随机样本
batch_indices = example_indices[i: i + batch_size] # 当前batch的各个样本的首字符的下标
X = [_data(j) for j in batch_indices]
Y = [_data(j + 1) for j in batch_indices]
yield torch.tensor(X, device=device), torch.tensor(Y, device=device)
my_seq = list(range(30))
for X, Y in data_iter_random(my_seq, batch_size=2, num_steps=6):
print('X: ', X, '\nY:', Y, '\n')
def data_iter_consecutive(corpus_indices, batch_size, num_steps, device=None):
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
corpus_len = len(corpus_indices) // batch_size * batch_size # 保留下来的序列的长度
corpus_indices = corpus_indices[: corpus_len] # 仅保留前corpus_len个字符
indices = torch.tensor(corpus_indices, device=device)
indices = indices.view(batch_size, -1) # resize成(batch_size, )
batch_num = (indices.shape[1] - 1) // num_steps
for i in range(batch_num):
i = i * num_steps
X = indices[:, i: i + num_steps]
Y = indices[:, i + 1: i + num_steps + 1]
yield X, Y
for X, Y in data_iter_consecutive(my_seq, batch_size=2, num_steps=6):
print('X: ', X, '\nY:', Y, '\n')
循环神经网络基础
循环神经网络
循环神经网络的构建
采用相邻采样仅在每个训练周期开始的时候初始化隐藏状态是因为相邻的两个批量在原始数据上是连续的
