challenging-america-word-gap-prediction-neural/run.ipynb

import torch
from torch import nn

vocab_size = 20000
embed_size = 100

class SimpleTrigramNeuralLanguageModel(nn.Module):
    def __init__(self, vocabulary_size, embedding_size):
        super(SimpleTrigramNeuralLanguageModel, self).__init__()
        self.embedding = nn.Embedding(vocabulary_size, embedding_size)
        self.linear = nn.Linear(embedding_size, vocabulary_size)

    def forward(self, x):
        x = self.embedding(x)
        x = self.linear(x)
        x = torch.softmax(x, dim=1)
        return x

import regex as re
from itertools import islice, chain
from torchtext.vocab import build_vocab_from_iterator
from torch.utils.data import IterableDataset

def get_words_from_line(line):
    line = line.rstrip()
    yield '<s>'
    for m in re.finditer(r'[\p{L}0-9\*]+|\p{P}+', line):
        yield m.group(0).lower()
    yield '</s>'

def get_word_lines_from_file(file_name):
    with open(file_name, 'r') as fh:
        for line in fh:
            yield get_words_from_line(line)
            
def look_ahead_iterator(gen):
    prev = None
    for item in gen:
        if prev is not None:
            yield (prev, item)
        prev = item

class Bigrams(IterableDataset):
    def __init__(self, text_file, vocabulary_size):
        self.vocab = build_vocab_from_iterator(
            get_word_lines_from_file(text_file),
            max_tokens = vocabulary_size,
            specials = ['<unk>']
        )
        self.vocab.set_default_index(self.vocab['<unk>'])
        self.vocabulary_size = vocabulary_size
        self.text_file = text_file

    def __iter__(self):
        return look_ahead_iterator((self.vocab[t] for t in chain.from_iterable(get_word_lines_from_file(self.text_file))))

from torch.utils.data import DataLoader

device = 'cuda'
train_dataset = Bigrams('europarl.txt', vocab_size)
model = SimpleTrigramNeuralLanguageModel(vocab_size, embed_size).to(device)
data = DataLoader(train_dataset, batch_size=2000)
optimizer = torch.optim.Adam(model.parameters())
criterion = torch.nn.NLLLoss()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
/tmp/ipykernel_16179/3272155308.py in <module>
      3 device = 'cuda'
      4 train_dataset = Bigrams('europarl.txt', vocab_size)
----> 5 model = SimpleTrigramNeuralLanguageModel(vocab_size, embed_size).to(device)
      6 data = DataLoader(train_dataset, batch_size=2000)
      7 optimizer = torch.optim.Adam(model.parameters())

/tmp/ipykernel_16179/1892442743.py in __init__(self, vocabulary_size, embedding_size)
      4 class SimpleTrigramNeuralLanguageModel(nn.Module):
      5     def __init__(self, vocabulary_size, embedding_size):
----> 6         super(SimpleBigramNeuralLanguageModel, self).__init__()
      7         self.embedding = nn.Embedding(vocabulary_size, embedding_size)
      8         self.linear = nn.Linear(embedding_size, vocabulary_size)

NameError: name 'SimpleBigramNeuralLanguageModel' is not defined

for epoch in range(1):
    model.train()
    for x, y in data:
        x = x.to(device)
        y = y.to(device)
        optimizer.zero_grad()
        outputs = model(x)
        loss = criterion(torch.log(outputs), y)
        if step % 100 == 0:
            print(step, loss)
        step += 1
        loss.backward()
        optimizer.step()
        
torch.save(model.state_dict(), 'model/model1.bin')