dl_task02

文本预处理

import collections
import re

def read_time_machine():
    with open('D:\\study\\a.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))

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)
print(tokens[0:2])


#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):
    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


vocab = Vocab(tokens)
print(list(vocab.token_to_idx.items())[0:10])


#将词转为索引
#使用字典，我们可以将原文本中的句子从单词序列转换为索引序列
for i in range(8, 10):
    print('words:', tokens[i])
    print('indices:', vocab[tokens[i]])



'''
用现有工具进行分词
我们前面介绍的分词方式非常简单，它至少有以下几个缺点:

标点符号通常可以提供语义信息，但是我们的方法直接将其丢弃了
类似“shouldn't", "doesn't"这样的词会被错误地处理
类似"Mr.", "Dr."这样的词会被错误地处理
我们可以通过引入更复杂的规则来解决这些问题，但是事实上，
有一些现有的工具可以很好地进行分词，我们在这里简单介绍其中的两个：spaCy和NLTK。

下面是一个简单的例子：

'''

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])


#NLTK:
from nltk.tokenize import word_tokenize
from nltk import data
data.path.append('D:\\study\\a.txt')
print(word_tokenize(text))

语言模型

import torch
import random

# 读取数据集
with open('D:\\study\\a.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]

##建立字符索引
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)


# 定义函数load_data_jay_lyrics，在后续章节中直接调用
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


# 时序数据的采样
'''
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。'''


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)


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


my_seq = list(range(10))
# for X, Y in data_iter_random(my_seq, batch_size=2, num_steps=6):
# print('X: ', X, '\nY:', Y, '\n')


for X, Y in data_iter_consecutive(my_seq, batch_size=2, num_steps=2):
    print('...X: ', X, '\nY:', Y, '\n')

循环神经网络基础