{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "NXTSugt6ieXh"
   },
   "source": [
    "## 訓練 CBoW 模型\n",
    "\n",
    "此筆記本是 [AI for Beginners Curriculum](http://aka.ms/ai-beginners) 的一部分\n",
    "\n",
    "在這個範例中，我們將學習如何訓練 CBoW 語言模型，以建立我們自己的 Word2Vec 嵌入空間。我們將使用 AG News 數據集作為文本來源。\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "import torch\n",
    "import torchtext\n",
    "import os\n",
    "import collections\n",
    "import builtins\n",
    "import random\n",
    "import numpy as np"
   ],
   "metadata": {
    "id": "q-UiiJUKaxHj"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "code",
   "source": [
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")"
   ],
   "metadata": {
    "id": "TFbR8CZaTZ1q"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "source": [
    "首先讓我們載入資料集並定義分詞器和詞彙表。我們將 `vocab_size` 設定為 5000 以稍微限制計算量。\n"
   ],
   "metadata": {
    "id": "HIwC7lI5T-ov"
   }
  },
  {
   "cell_type": "code",
   "source": [
    "def load_dataset(ngrams = 1, min_freq = 1, vocab_size = 5000 , lines_cnt = 500):\n",
    "    tokenizer = torchtext.data.utils.get_tokenizer('basic_english')\n",
    "    print(\"Loading dataset...\")\n",
    "    test_dataset, train_dataset  = torchtext.datasets.AG_NEWS(root='./data')\n",
    "    train_dataset = list(train_dataset)\n",
    "    test_dataset = list(test_dataset)\n",
    "    classes = ['World', 'Sports', 'Business', 'Sci/Tech']\n",
    "    print('Building vocab...')\n",
    "    counter = collections.Counter()\n",
    "    for i, (_, line) in enumerate(train_dataset):\n",
    "        counter.update(torchtext.data.utils.ngrams_iterator(tokenizer(line),ngrams=ngrams))\n",
    "        if i == lines_cnt:\n",
    "            break\n",
    "    vocab = torchtext.vocab.Vocab(collections.Counter(dict(counter.most_common(vocab_size))), min_freq=min_freq)\n",
    "    return train_dataset, test_dataset, classes, vocab, tokenizer"
   ],
   "metadata": {
    "id": "wdZuygtgiuLG"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "code",
   "source": [
    "train_dataset, test_dataset, _, vocab, tokenizer = load_dataset()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4d1nU1gsivGu",
    "outputId": "949fe272-ae0e-49f5-c373-6703458b3a74"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Loading dataset...\n",
      "Building vocab...\n"
     ]
    }
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "def encode(x, vocabulary, tokenizer = tokenizer):\n",
    "    return [vocabulary[s] for s in tokenizer(x)]"
   ],
   "metadata": {
    "id": "1XDYNhG8ToFV"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "LIlQk6_PaHVY"
   },
   "source": [
    "## CBoW 模型\n",
    "\n",
    "CBoW 學習根據 $2N$ 個相鄰的單詞來預測一個單詞。例如，當 $N=1$ 時，我們可以從句子 *I like to train networks* 中得到以下配對：(like, I)、(I, like)、(to, like)、(like, to)、(train, to)、(to, train)、(networks, train)、(train, networks)。在這裡，第一個單詞是作為輸入的相鄰單詞，第二個單詞是我們要預測的單詞。\n",
    "\n",
    "為了構建一個用於預測下一個單詞的網絡，我們需要提供相鄰單詞作為輸入，並獲得單詞編號作為輸出。CBoW 網絡的架構如下：\n",
    "\n",
    "* 輸入單詞會通過嵌入層。這個嵌入層就是我們的 Word2Vec 嵌入，因此我們會將其單獨定義為 `embedder` 變數。在這個例子中，我們將使用嵌入大小為 30，儘管你可能想嘗試更高的維度（真實的 Word2Vec 通常是 300 維）。\n",
    "* 嵌入向量接著會傳遞到一個線性層，該層將預測輸出單詞。因此它有 `vocab_size` 個神經元。\n",
    "\n",
    "對於輸出，如果我們使用 `CrossEntropyLoss` 作為損失函數，我們只需要提供單詞編號作為期望結果，而不需要使用 one-hot 編碼。\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "vocab_size = len(vocab)\n",
    "\n",
    "embedder = torch.nn.Embedding(num_embeddings = vocab_size, embedding_dim = 30)\n",
    "model = torch.nn.Sequential(\n",
    "    embedder,\n",
    "    torch.nn.Linear(in_features = 30, out_features = vocab_size),\n",
    ")\n",
    "\n",
    "print(model)"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "akKTcKQKkfl2",
    "outputId": "da687e3e-a8ec-4c1a-e456-ab8cd6ac7dad"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Sequential(\n",
      "  (0): Embedding(5002, 30)\n",
      "  (1): Linear(in_features=30, out_features=5002, bias=True)\n",
      ")\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Nud6jgGPaHVa"
   },
   "source": [
    "## 準備訓練數據\n",
    "\n",
    "現在讓我們編寫主要函數，從文本中計算 CBoW 詞對。這個函數將允許我們指定窗口大小，並返回一組詞對——輸入詞和輸出詞。請注意，這個函數既可以用於詞，也可以用於向量/張量——這將使我們能夠在傳遞給 `to_cbow` 函數之前對文本進行編碼。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "x-dsXygOieXn",
    "outputId": "c2218280-e540-40ba-9546-efe48d0d714f"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[['like', 'I'], ['to', 'I'], ['I', 'like'], ['to', 'like'], ['train', 'like'], ['I', 'to'], ['like', 'to'], ['train', 'to'], ['networks', 'to'], ['like', 'train'], ['to', 'train'], ['networks', 'train'], ['to', 'networks'], ['train', 'networks']]\n",
      "[[232, 172], [5, 172], [172, 232], [5, 232], [0, 232], [172, 5], [232, 5], [0, 5], [1202, 5], [232, 0], [5, 0], [1202, 0], [5, 1202], [0, 1202]]\n"
     ]
    }
   ],
   "source": [
    "def to_cbow(sent,window_size=2):\n",
    "    res = []\n",
    "    for i,x in enumerate(sent):\n",
    "        for j in range(max(0,i-window_size),min(i+window_size+1,len(sent))):\n",
    "            if i!=j:\n",
    "                res.append([sent[j],x])\n",
    "    return res\n",
    "\n",
    "print(to_cbow(['I','like','to','train','networks']))\n",
    "print(to_cbow(encode('I like to train networks', vocab)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XVaaDLjaaHVb"
   },
   "source": [
    "讓我們準備訓練數據集。我們將遍歷所有新聞，調用 `to_cbow` 來獲取詞對列表，並將這些詞對添加到 `X` 和 `Y` 中。為了節省時間，我們只考慮前 10k 條新聞項目——如果你有更多時間等待並希望獲得更好的嵌入，可以輕鬆移除這個限制 :)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "54b-Gd9TieXo"
   },
   "outputs": [],
   "source": [
    "X = []\n",
    "Y = []\n",
    "for i, x in zip(range(10000), train_dataset):\n",
    "    for w1, w2 in to_cbow(encode(x[1], vocab), window_size = 5):\n",
    "        X.append(w1)\n",
    "        Y.append(w2)\n",
    "\n",
    "X = torch.tensor(X)\n",
    "Y = torch.tensor(Y)"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "我們還將把該數據轉換為一個數據集，並創建數據加載器：\n"
   ],
   "metadata": {
    "id": "cwWy0PzXWhN5"
   }
  },
  {
   "cell_type": "code",
   "source": [
    "class SimpleIterableDataset(torch.utils.data.IterableDataset):\n",
    "    def __init__(self, X, Y):\n",
    "        super(SimpleIterableDataset).__init__()\n",
    "        self.data = []\n",
    "        for i in range(len(X)):\n",
    "            self.data.append( (Y[i], X[i]) )\n",
    "        random.shuffle(self.data)\n",
    "\n",
    "    def __iter__(self):\n",
    "        return iter(self.data)"
   ],
   "metadata": {
    "id": "mfoAcGPFZU8p"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "e4NQ_-5waHVc"
   },
   "source": [
    "我們還將把該數據轉換為一個數據集，並創建數據加載器：\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "AbLUcojlieXo"
   },
   "outputs": [],
   "source": [
    "ds = SimpleIterableDataset(X, Y)\n",
    "dl = torch.utils.data.DataLoader(ds, batch_size = 256)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "pKQr7sXeaHVc"
   },
   "source": [
    "現在讓我們進行實際訓練。我們將使用 `SGD` 優化器，並設定相當高的學習率。你也可以嘗試使用其他優化器，例如 `Adam`。我們將先訓練 10 個世代——如果你希望更低的損失，可以重新執行此單元格。\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "def train_epoch(net, dataloader, lr = 0.01, optimizer = None, loss_fn = torch.nn.CrossEntropyLoss(), epochs = None, report_freq = 1):\n",
    "    optimizer = optimizer or torch.optim.Adam(net.parameters(), lr = lr)\n",
    "    loss_fn = loss_fn.to(device)\n",
    "    net.train()\n",
    "\n",
    "    for i in range(epochs):\n",
    "        total_loss, j = 0, 0, \n",
    "        for labels, features in dataloader:\n",
    "            optimizer.zero_grad()\n",
    "            features, labels = features.to(device), labels.to(device)\n",
    "            out = net(features)\n",
    "            loss = loss_fn(out, labels)\n",
    "            loss.backward()\n",
    "            optimizer.step()\n",
    "            total_loss += loss\n",
    "            j += 1\n",
    "        if i % report_freq == 0:\n",
    "            print(f\"Epoch: {i+1}: loss={total_loss.item()/j}\")\n",
    "\n",
    "    return total_loss.item()/j"
   ],
   "metadata": {
    "id": "HeeCYKr_KF1w"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "code",
   "source": [
    "train_epoch(net = model, dataloader = dl, optimizer = torch.optim.SGD(model.parameters(), lr = 0.1), loss_fn = torch.nn.CrossEntropyLoss(), epochs = 10)"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "KVgwGtDHgDlT",
    "outputId": "2447833f-f0e3-4566-c33d-addbfe2f451d"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Epoch: 1: loss=5.664632366860172\n",
      "Epoch: 2: loss=5.632101973960962\n",
      "Epoch: 3: loss=5.610399051405015\n",
      "Epoch: 4: loss=5.594621561080262\n",
      "Epoch: 5: loss=5.582538017415446\n",
      "Epoch: 6: loss=5.572900234519603\n",
      "Epoch: 7: loss=5.564951676341915\n",
      "Epoch: 8: loss=5.558288112064614\n",
      "Epoch: 9: loss=5.552576955031129\n",
      "Epoch: 10: loss=5.547634165194347\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "5.547634165194347"
      ]
     },
     "metadata": {},
     "execution_count": 16
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "W8u2qXZmaHVd"
   },
   "source": [
    "## 嘗試使用 Word2Vec\n",
    "\n",
    "要使用 Word2Vec，我們來提取與詞彙表中所有單詞對應的向量：\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "r8TatcXjkU_t"
   },
   "outputs": [],
   "source": [
    "vectors = torch.stack([embedder(torch.tensor(vocab[s])) for s in vocab.itos], 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "3OcX21UOaHVd"
   },
   "source": [
    "讓我們看看，例如，單詞**Paris**是如何被編碼成一個向量的：\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bz6tAeLzieXp",
    "outputId": "5b20850e-4342-45e9-f840-cfac2b4d61d8"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "tensor([-0.0915,  2.1224, -0.0281, -0.6819,  1.1219,  0.6458, -1.3704, -1.3314,\n",
      "        -1.1437,  0.4496,  0.2301, -0.3515, -0.8485,  1.0481,  0.4386, -0.8949,\n",
      "         0.5644,  1.0939, -2.5096,  3.2949, -0.2601, -0.8640,  0.1421, -0.0804,\n",
      "        -0.5083, -1.0560,  0.9753, -0.5949, -1.6046,  0.5774],\n",
      "       grad_fn=<EmbeddingBackward>)\n"
     ]
    }
   ],
   "source": [
    "paris_vec = embedder(torch.tensor(vocab['paris']))\n",
    "print(paris_vec)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "pHTJlaeYaHVd"
   },
   "source": [
    "使用 Word2Vec 來尋找同義詞是很有趣的。以下函數將返回與給定輸入最接近的 `n` 個詞。為了找到它們，我們計算 $|w_i - v|$ 的範數，其中 $v$ 是對應於我們輸入詞的向量，$w_i$ 是詞彙表中第 $i$ 個詞的編碼。我們接著對陣列進行排序，並使用 `argsort` 返回相應的索引，然後取列表的前 `n` 個元素，這些元素編碼了詞彙表中最接近詞的位置。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "NlZyi-_olFar",
    "outputId": "b5dbb163-88c4-4d5a-eaf2-6751f700e98c"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "['microsoft', 'quoted', 'lp', 'rate', 'top']"
      ]
     },
     "metadata": {},
     "execution_count": 56
    }
   ],
   "source": [
    "def close_words(x, n = 5):\n",
    "  vec = embedder(torch.tensor(vocab[x]))\n",
    "  top5 = np.linalg.norm(vectors.detach().numpy() - vec.detach().numpy(), axis = 1).argsort()[:n]\n",
    "  return [ vocab.itos[x] for x in top5 ]\n",
    "\n",
    "close_words('microsoft')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-dQq7xeAln0U",
    "outputId": "66f768c3-c248-4bfd-ce4f-c8ffc6d0dd0d"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "['basketball', 'lot', 'sinai', 'states', 'healthdaynews']"
      ]
     },
     "metadata": {},
     "execution_count": 51
    }
   ],
   "source": [
    "close_words('basketball')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "fJXqK26b29sa",
    "outputId": "78f0baba-ffd0-485a-dd87-0a12bedfd7fa"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "['funds', 'travel', 'sydney', 'japan', 'business']"
      ]
     },
     "metadata": {},
     "execution_count": 77
    }
   ],
   "source": [
    "close_words('funds')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "My0VeTDd3Ji8"
   },
   "source": [
    "## 重點\n",
    "\n",
    "使用像 CBoW 這樣的巧妙技術，我們可以訓練 Word2Vec 模型。你也可以嘗試訓練 skip-gram 模型，該模型是基於給定中心詞來預測鄰近詞，看看它的表現如何。\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n---\n\n**免責聲明**：  \n本文件已使用 AI 翻譯服務 [Co-op Translator](https://github.com/Azure/co-op-translator) 進行翻譯。儘管我們努力確保翻譯的準確性，但請注意，自動翻譯可能包含錯誤或不準確之處。原始文件的母語版本應被視為權威來源。對於關鍵信息，建議使用專業人工翻譯。我們對因使用此翻譯而引起的任何誤解或誤釋不承擔責任。\n"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "CBoW-PyTorch.ipynb",
   "provenance": []
  },
  "interpreter": {
   "hash": "16af2a8bbb083ea23e5e41c7f5787656b2ce26968575d8763f2c4b17f9cd711f"
  },
  "kernelspec": {
   "display_name": "Python 3.8.12 ('py38')",
   "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": "3.8.12"
  },
  "orig_nbformat": 4,
  "gpuClass": "standard",
  "coopTranslator": {
   "original_hash": "36df28efe3fe40b6fb0a7fa48fe3ea82",
   "translation_date": "2025-08-28T12:05:19+00:00",
   "source_file": "lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb",
   "language_code": "mo"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}