词表映射Vocab

在进行自然语言处理过程中需要将自然语言转化成数字化表示，需要对自然语言进行词表映射。

from collections import defaultdict

#建立词表映射
class Vocab:
    def __init__(self,tokens=None):
        self.idx_to_token = list()
        self.token_to_idx = dict()
        if tokens is not None:
            if "" not in tokens:
                tokens = tokens + [""]
            for token in tokens:
                self.idx_to_token.append(token)
                self.token_to_idx[token] = len(self.idx_to_token) - 1
            self.unk = self.token_to_idx['']
	
	#创建词表
    @classmethod
    def build(cls,text,min_freq=1,reserved_tokens=None):
        token_freqs = defaultdict(int)  
        for sentence in text:
            for token in sentence:
                token_freqs[token] += 1
        uniq_tokens = [""] + (reserved_tokens if reserved_tokens else [])
        uniq_tokens += [token for token,freq in token_freqs.items() if freq >= min_freq and token != ""]
        return cls(uniq_tokens)
        
     #返回词表大小
	def __len__(self):
        return len(self.idx_to_token)
    
    #查找token索引
    def __getitem__(self,token):
        return self.token_to_idx.get(token,self.unk)

	#将tokens转化成索引      
    def convert_tokens_ids(self,tokens):
        return [self.token_to_idx[token] for token in tokens]
    
    #将索引转化成token
    def convert_ids_to_tokens(self,indices):
        return [self.idx_to_token[index] for index in indices]

#验证
from nltk.corpus import sentence_polarity
vocab = Vocab.build(sentence_polarity.sents())
print("词表大小：",len(vocab))
print('great的索引：',vocab['great'])
print("token转换成id：",vocab.convert_tokens_ids(['i','am','great']))
print("id转化成token：",vocab.convert_ids_to_tokens([329, 4499, 3495]))			 

使用BERT等预训练模型，自带词表，不需要创建词表。