动手学深度学习之文本预处理

文本预处理

import collections
import re
from d2l import torch as d2l

将数据集读取到由文本行组成的列表中

d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
                                '090b5e7e70c295757f55df93cb0a180b9691891a')  # load一本书

def read_time_machine():  
    """Load the time machine dataset into a list of text lines."""
    with open(d2l.download('time_machine'), 'r') as f:
        lines = f.readlines()
    return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]  # 将不是字母的东西全部变为空格

lines = read_time_machine()
print(lines[0])
print(lines[10])

Downloading ../data/timemachine.txt from http://d2l-data.s3-accelerate.amazonaws.com/timemachine.txt...
the time machine by h g wells
twinkled and his usually pale face was flushed and animated the

每个文本序列被拆分成一个标记列表

# 这个函数的作用就是将一行转换为一个个token，这个token要么是一个字符串要么是一个词
def tokenize(lines, token='word'):  
    """将文本行拆分为单词或字符标记。"""
    if token == 'word':  # 一个字符串
        return [line.split() for line in lines]
    elif token == 'char':
        return [list(line) for line in lines]
    else:
        print('错误：未知令牌类型：' + token)

tokens = tokenize(lines)
for i in range(11):
    print(tokens[i])

['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
[]
[]
[]
[]
['i']
[]
[]
['the', 'time', 'traveller', 'for', 'so', 'it', 'will', 'be', 'convenient', 'to', 'speak', 'of', 'him']
['was', 'expounding', 'a', 'recondite', 'matter', 'to', 'us', 'his', 'grey', 'eyes', 'shone', 'and']
['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']

构建一个字典，通常也叫做词表（vocabulary），用来将字符串标记映射到从0开始的数字索引中

class Vocab:  
    """文本词表"""
    def __init__(self, tokens=None, min_freq=0, reserved_tokens=None):  # 如果一个token在文本序列里面出现的次数少于min_freq词我们就将它丢掉
        if tokens is None:
            tokens = []
        if reserved_tokens is None:
            reserved_tokens = []
        counter = count_corpus(tokens)
        self.token_freqs = sorted(counter.items(), key=lambda x: x[1],
                                  reverse=True)  # 如果我们有每个token出现的频率的话，我们就将它sort一下，从大排到小
        self.unk, uniq_tokens = 0, ['<unk>'] + reserved_tokens  # 这里有个unknow token这就是位置的token
        uniq_tokens += [
            token for token, freq in self.token_freqs
            if freq >= min_freq and token not in uniq_tokens]  # 意思就是将token次数大于等于min_freq的东西放到这里，小于的就丢掉
        self.idx_to_token, self.token_to_idx = [], dict()  # 给一个token返回一个index
        for token in uniq_tokens:
            self.idx_to_token.append(token)
            self.token_to_idx[token] = len(self.idx_to_token) - 1

    def __len__(self):
        return len(self.idx_to_token)  # uniq_token的个数

    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]  # 返回index

    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]  # 给一个下标返回一个token

def count_corpus(tokens):  # 计算每个token出现的次数
    """统计标记的频率。"""
    if len(tokens) == 0 or isinstance(tokens[0], list):
        tokens = [token for line in tokens for token in line]
    return collections.Counter(tokens)

构建词汇表

vocab = Vocab(tokens)  # 构造一个vacab
print(list(vocab.token_to_idx.items())[:10])

[('<unk>', 0), ('the', 1), ('i', 2), ('and', 3), ('of', 4), ('a', 5), ('to', 6), ('was', 7), ('in', 8), ('that', 9)]

将每一行文本转换成一个数字索引列表

for i in [0, 10]:
    print('words:', tokens[i])
    print('indices:', vocab[tokens[i]])

words: ['the', 'time', 'machine', 'by', 'h', 'g', 'wells']
indices: [1, 19, 50, 40, 2183, 2184, 400]
words: ['twinkled', 'and', 'his', 'usually', 'pale', 'face', 'was', 'flushed', 'and', 'animated', 'the']
indices: [2186, 3, 25, 1044, 362, 113, 7, 1421, 3, 1045, 1]

将所有内容打包到load_corpus_time_machine函数中

def load_corpus_time_machine(max_tokens=-1):  
    """返回时光机器数据集的标记索引列表和词汇表。"""
    lines = read_time_machine()
    tokens = tokenize(lines, 'char')
    vocab = Vocab(tokens)
    corpus = [vocab[token] for line in tokens for token in line]  # 将每一个行都丢进vacublary里面转换为数字下标
    if max_tokens > 0:
        corpus = corpus[:max_tokens]
    return corpus, vocab

corpus, vocab = load_corpus_time_machine()
len(corpus), len(vocab)

(170580, 28)