{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "d42ddd87",
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from torch import nn"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "dc73124c",
"metadata": {},
"outputs": [],
"source": [
"vocab_size = 20000\n",
"embed_size = 100\n",
"\n",
"class SimpleTrigramNeuralLanguageModel(nn.Module):\n",
" def __init__(self, vocabulary_size, embedding_size):\n",
" super(SimpleTrigramNeuralLanguageModel, self).__init__()\n",
" self.embedding = nn.Embedding(vocabulary_size, embedding_size)\n",
" self.linear = nn.Linear(embedding_size, vocabulary_size)\n",
"\n",
" def forward(self, x):\n",
" x = self.embedding(x)\n",
" x = self.linear(x)\n",
" x = torch.softmax(x, dim=1)\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "569b4c88",
"metadata": {},
"outputs": [],
"source": [
"import regex as re\n",
"from itertools import islice, chain\n",
"from torchtext.vocab import build_vocab_from_iterator\n",
"from torch.utils.data import IterableDataset\n",
"\n",
"def get_words_from_line(line):\n",
" line = line.rstrip()\n",
" yield ''\n",
" for m in re.finditer(r'[\\p{L}0-9\\*]+|\\p{P}+', line):\n",
" yield m.group(0).lower()\n",
" yield ''\n",
"\n",
"def get_word_lines_from_file(file_name):\n",
" with open(file_name, 'r') as fh:\n",
" for line in fh:\n",
" yield get_words_from_line(line)\n",
" \n",
"def look_ahead_iterator(gen):\n",
" prev = None\n",
" for item in gen:\n",
" if prev is not None:\n",
" yield (prev, item)\n",
" prev = item"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "f95cb913",
"metadata": {},
"outputs": [],
"source": [
"class Bigrams(IterableDataset):\n",
" def __init__(self, text_file, vocabulary_size):\n",
" self.vocab = build_vocab_from_iterator(\n",
" get_word_lines_from_file(text_file),\n",
" max_tokens = vocabulary_size,\n",
" specials = ['']\n",
" )\n",
" self.vocab.set_default_index(self.vocab[''])\n",
" self.vocabulary_size = vocabulary_size\n",
" self.text_file = text_file\n",
"\n",
" def __iter__(self):\n",
" return look_ahead_iterator((self.vocab[t] for t in chain.from_iterable(get_word_lines_from_file(self.text_file))))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7a51f2b1",
"metadata": {},
"outputs": [],
"source": [
"from torch.utils.data import DataLoader\n",
"\n",
"device = 'cpu'\n",
"train_dataset = Bigrams('europarl.txt', vocab_size)\n",
"model = SimpleTrigramNeuralLanguageModel(vocab_size, embed_size).to(device)\n",
"data = DataLoader(train_dataset, batch_size=2000)\n",
"optimizer = torch.optim.Adam(model.parameters())\n",
"criterion = torch.nn.NLLLoss()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "474194ae",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 tensor(10.0424, grad_fn=)\n",
"100 tensor(7.9016, grad_fn=)\n",
"200 tensor(7.1964, grad_fn=)\n",
"300 tensor(6.5661, grad_fn=)\n",
"400 tensor(6.4146, grad_fn=)\n",
"500 tensor(5.8718, grad_fn=)\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[0my\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 9\u001b[1;33m \u001b[0moutputs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 10\u001b[0m \u001b[0mloss\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcriterion\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 11\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstep\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;36m100\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m 1108\u001b[0m if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks\n\u001b[0;32m 1109\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[1;32m-> 1110\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1111\u001b[0m \u001b[1;31m# Do not call functions when jit is used\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1112\u001b[0m \u001b[0mfull_backward_hooks\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m\u001b[0m in \u001b[0;36mforward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m 10\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 11\u001b[0m \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0membedding\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 13\u001b[0m \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msoftmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m 1108\u001b[0m if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks\n\u001b[0;32m 1109\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[1;32m-> 1110\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1111\u001b[0m \u001b[1;31m# Do not call functions when jit is used\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1112\u001b[0m \u001b[0mfull_backward_hooks\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\linear.py\u001b[0m in \u001b[0;36mforward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m 101\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 102\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 103\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mF\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbias\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 105\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mextra_repr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"step = 0\n",
"\n",
"for epoch in range(1):\n",
" model.train()\n",
" for x, y in data:\n",
" x = x.to(device)\n",
" y = y.to(device)\n",
" optimizer.zero_grad()\n",
" outputs = model(x)\n",
" loss = criterion(torch.log(outputs), y)\n",
" if step % 100 == 0:\n",
" print(step, loss)\n",
" step += 1\n",
" loss.backward()\n",
" optimizer.step()\n",
" \n",
"torch.save(model.state_dict(), 'model/model1.bin')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "alpha-leonard",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}