语言模型数据处理

data = [("me gusta comer en la cafeteria".split(), "SPANISH"),
        ("Give it to me".split(), "ENGLISH"),
        ("No creo que sea una buena idea".split(), "SPANISH"),
        ("No it is not a good idea to get lost at sea".split(), "ENGLISH")]

word_to_ix = {}
for sent, _ in data + test_data:
    for word in sent:
        if word not in word_to_ix:
            word_to_ix[word] = len(word_to_ix)
print(word_to_ix)
print (word)

import os
import torch
from collections import Counter
class (object):
    def __init__(self):
        self.word2idx = {}
        self.idx2word = []
        self.counter = Counter()
        self.total = 0
    def add_word(self, word):
        if word not in self.word2idx:
            self.idx2word.append(word)
            self.word2idx[word] = len(self.idx2word) - 1
        token_id = self.word2idx[word]
        self.counter[token_id] += 1
        self.total += 1
        return self.word2idx[word]
    def __len__(self):
        return len(self.idx2word)
class Corpus(object):
    def __init__(self, path):
        self.dictionary = Dictionary()
        self.train = self.tokenize(os.path.join(path, 'train.txt'))
        self.valid = self.tokenize(os.path.join(path, 'valid.txt'))
        self.test = self.tokenize(os.path.join(path, 'test.txt'))
    def tokenize(self, path):
        """Tokenizes a text file."""
        assert os.path.exists(path)
        
        with open(path, 'r') as f:
            tokens = 0
            for line in f:
                words = line.split() + ['<eos>']
                tokens += len(words)
                for word in words:
                    self.dictionary.add_word(word)
        # Tokenize file content
        with open(path, 'r') as f:
            ids = torch.LongTensor(tokens)
            token = 0
            for line in f:
                words = line.split() + ['<eos>']
                for word in words:
                    ids[token] = self.dictionary.word2idx[word]
                    token += 1
        return ids