动手学深度学习PyTorch版-文本预处理

最新推荐文章于 2024-05-22 18:53:14 发布

hongyesuifeng

最新推荐文章于 2024-05-22 18:53:14 发布

阅读量195

点赞数

分类专栏： python 机器学习

本文链接：https://blog.csdn.net/hongyesuifeng/article/details/104304637

版权

python 同时被 2 个专栏收录

51 篇文章 0 订阅

订阅专栏

机器学习

49 篇文章 1 订阅

订阅专栏

本文介绍了如何进行深度学习中文本预处理的步骤，包括读入文本、分词、建立字典以及将词转换为索引。通过实例展示了具体的处理过程，便于理解并应用于实际项目。

摘要由CSDN通过智能技术生成

文本预处理

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

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]

[[‘the’, ‘time’, ‘machine’, ‘by’, ‘h’, ‘g’, ‘wells’, ‘’], [’’]]
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
vocab = Vocab(tokens)
print(list(vocab.token_to_idx.items())[0:10])

[(’’, 0), (‘the’, 1), (‘time’, 2), (‘machine’, 3), (‘by’, 4), (‘h’, 5), (‘g’, 6), (‘wells’, 7), (‘i’, 8), (‘traveller’, 9)]
将词转为索引

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

words: [‘the’, ‘time’, ‘traveller’, ‘for’, ‘so’, ‘it’, ‘will’, ‘be’, ‘convenient’, ‘to’, ‘speak’, ‘of’, ‘him’, ‘’]
indices: [1, 2, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 0]
words: [‘was’, ‘expounding’, ‘a’, ‘recondite’, ‘matter’, ‘to’, ‘us’, ‘his’, ‘grey’, ‘eyes’, ‘shone’, ‘and’]
indices: [20, 21, 22, 23, 24, 16, 25, 26, 27, 28, 29, 30]
分词工具使用

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))