{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "*italicized text*\n",
        "\n",
        "# **End to End Japanes VS English Seq2Seq Translator**\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "PckPN64C89q1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install sacrebleu\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.utils.data import DataLoader, Dataset\n",
        "import numpy as np\n",
        "import sacrebleu\n",
        "import json\n",
        "import matplotlib.pyplot as plt\n",
        "import csv\n",
        "import json\n",
        "import re\n"
      ],
      "metadata": {
        "id": "wUQs4mOmlcEJ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1c454200-c93a-4a9b-86d1-8a1116905511"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting sacrebleu\n",
            "  Downloading sacrebleu-2.4.3-py3-none-any.whl.metadata (51 kB)\n",
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/51.8 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.8/51.8 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting portalocker (from sacrebleu)\n",
            "  Downloading portalocker-2.10.1-py3-none-any.whl.metadata (8.5 kB)\n",
            "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (2024.9.11)\n",
            "Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (0.9.0)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (1.26.4)\n",
            "Collecting colorama (from sacrebleu)\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl.metadata (17 kB)\n",
            "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (5.3.0)\n",
            "Downloading sacrebleu-2.4.3-py3-none-any.whl (103 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.0/104.0 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Downloading portalocker-2.10.1-py3-none-any.whl (18 kB)\n",
            "Installing collected packages: portalocker, colorama, sacrebleu\n",
            "Successfully installed colorama-0.4.6 portalocker-2.10.1 sacrebleu-2.4.3\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import json\n",
        "import re\n",
        "\n",
        "# Function to clean invalid escape sequences in JSON file\n",
        "def clean_json(file_path):\n",
        "    with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:\n",
        "        content = f.read()\n",
        "    # Remove invalid \\uXXXX sequences using regex\n",
        "    content = re.sub(r'\\\\u[0-9A-Fa-f]{0,3}(?![0-9A-Fa-f])', '', content)\n",
        "    return content\n",
        "\n",
        "# Path to the JSON file\n",
        "file_path = '/content/Japanes.json'\n",
        "\n",
        "try:\n",
        "    # Clean the JSON content\n",
        "    cleaned_content = clean_json(file_path)\n",
        "    # Parse the cleaned JSON content\n",
        "    data = json.loads(cleaned_content)\n",
        "    print(\"JSON loaded successfully.\")\n",
        "\n",
        "    # Extract sentences from the first 1000 entries\n",
        "    en_sentences = [entry['input'] for entry in data[:1000]]\n",
        "    ja_sentences = [entry['output'] for entry in data[:1000]]\n",
        "    print(f\"Loaded {len(en_sentences)} English and Japanes sentence pairs.\")\n",
        "except json.JSONDecodeError as e:\n",
        "    print(f\"Error decoding JSON: {e}\")\n",
        "except KeyError as e:\n",
        "    print(f\"Key error: {e}\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PpaV8fo6pLQc",
        "outputId": "18312d69-fd6d-4ade-cd6c-909f0e78ac58"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "JSON loaded successfully.\n",
            "Loaded 1000 English and Japanes sentence pairs.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "# Hyperparameters\n",
        "MAX_LEN = 60\n",
        "DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
        "VOCAB_SIZE = 20000\n",
        "EMBEDDING_DIM = 256\n",
        "HIDDEN_DIM = 512\n",
        "BATCH_SIZE = 32\n",
        "NUM_EPOCHS = 10\n",
        "\n",
        "tokenizer = lambda x: x.split()\n",
        "\n",
        "# Build vocabulary\n",
        "def build_vocab(sentences):\n",
        "    counter = {}\n",
        "    for sentence in sentences:\n",
        "        for token in tokenizer(sentence):\n",
        "            counter[token] = counter.get(token, 0) + 1\n",
        "    return {word: idx + 4 for idx, (word, _) in enumerate(counter.items())}\n",
        "\n",
        "en_vocab = {'<pad>': 0, '<s>': 1, '</s>': 2, '<unk>': 3, **build_vocab(en_sentences)}\n",
        "bu_vocab = {'<pad>': 0, '<s>': 1, '</s>': 2, '<unk>': 3, **build_vocab(ja_sentences)}  # Lowercase 'ja_sentences'\n",
        "\n",
        "# Convert sentences to tensors\n",
        "def sentence_to_tensor(sentence, vocab, max_len=MAX_LEN):\n",
        "    tokens = [vocab.get(word, vocab['<unk>']) for word in tokenizer(sentence)]\n",
        "    return torch.tensor([vocab['<s>']] + tokens + [vocab['</s>']] + [vocab['<pad>']] * (max_len - len(tokens) - 2))[:max_len]\n",
        "\n",
        "en_tensor_sentences = [sentence_to_tensor(s, en_vocab) for s in en_sentences]\n",
        "ja_tensor_sentences = [sentence_to_tensor(s, bu_vocab) for s in ja_sentences]  # Lowercase 'bu_tensor_sentences'\n",
        "\n",
        "# Split into training and validation sets\n",
        "train_size = int(len(en_tensor_sentences) * 0.8)\n",
        "train_en, val_en = en_tensor_sentences[:train_size], en_tensor_sentences[train_size:]\n",
        "train_ja, val_ja = ja_tensor_sentences[:train_size], ja_tensor_sentences[train_size:]  # Lowercase 'train_bu' and 'val_bu'\n"
      ],
      "metadata": {
        "id": "XPRLsJrDlcIY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "f3XZNpV7oyc3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def print_sample_data(en_sentences, bu_sentences):\n",
        "    for i in range(4):\n",
        "        en_sample, bu_sample = en_sentences[i], bu_sentences[i]\n",
        "        print(f\"EN to JA\\n<s>\\n<en> {en_sample} </en>\\n<ja> {bu_sample} </ja>\\n</s>\")\n",
        "        print(f\"JA to EN\\n<s>\\n<ja> {bu_sample} </ja>\\n<en> {en_sample} </en>\\n</s>\\n\")\n",
        "\n",
        "# Call the function with English and Bulgarian sentences\n",
        "print_sample_data(en_sentences, ja_sentences)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L-DNniKxmyZi",
        "outputId": "5a3e7425-b2d5-4e5f-eac0-f68902fe2b67"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "EN to JA\n",
            "<s>\n",
            "<en> Give three tips for staying healthy. </en>\n",
            "<ja> 健康を維持するための3つのヒントを教えてください。 </ja>\n",
            "</s>\n",
            "JA to EN\n",
            "<s>\n",
            "<ja> 健康を維持するための3つのヒントを教えてください。 </ja>\n",
            "<en> Give three tips for staying healthy. </en>\n",
            "</s>\n",
            "\n",
            "EN to JA\n",
            "<s>\n",
            "<en> 1. Eat a balanced and nutritious diet: Make sure your meals are inclusive of a variety of fruits and vegetables, lean protein, whole grains, and healthy fats. This helps to provide your body with the essential nutrients to function at its best and can help prevent chronic diseases.\n",
            "\n",
            "2. Engage in regular physical activity: Exercise is crucial for maintaining strong bones, muscles, and cardiovascular health. Aim for at least 150 minutes of moderate aerobic exercise or 75 minutes of vigorous exercise each week.\n",
            "\n",
            "3. Get enough sleep: Getting enough quality sleep is crucial for physical and mental well-being. It helps to regulate mood, improve cognitive function, and supports healthy growth and immune function. Aim for 7-9 hours of sleep each night. </en>\n",
            "<ja>  1. バランスの取れた栄養価の高い食事を摂る: 食事にはさまざまな果物や野菜、脂肪分の少ないタンパク質、全粒穀物、健康的な脂肪が含まれていることを確認してください。これは体が最高の状態で機能するために必須の栄養素を提供するのに役立ち、慢性疾患の予防に役立ちます。 2. 定期的な身体活動に参加する: 強い骨、筋肉、心臓血管の健康を維持するには、運動が不可欠です。毎週少なくとも 150 分間の中程度の有酸素運動、または 75 分間の激しい運動を目標にしましょう。 3. 十分な睡眠をとる：質の高い睡眠を十分にとることは、身体的および精神的な健康にとって非常に重要です。気分を調整し、認知機能を改善し、健康な成長と免疫機能をサポートします。毎晩7〜9時間の睡眠を目指しましょう。 </ja>\n",
            "</s>\n",
            "JA to EN\n",
            "<s>\n",
            "<ja>  1. バランスの取れた栄養価の高い食事を摂る: 食事にはさまざまな果物や野菜、脂肪分の少ないタンパク質、全粒穀物、健康的な脂肪が含まれていることを確認してください。これは体が最高の状態で機能するために必須の栄養素を提供するのに役立ち、慢性疾患の予防に役立ちます。 2. 定期的な身体活動に参加する: 強い骨、筋肉、心臓血管の健康を維持するには、運動が不可欠です。毎週少なくとも 150 分間の中程度の有酸素運動、または 75 分間の激しい運動を目標にしましょう。 3. 十分な睡眠をとる：質の高い睡眠を十分にとることは、身体的および精神的な健康にとって非常に重要です。気分を調整し、認知機能を改善し、健康な成長と免疫機能をサポートします。毎晩7〜9時間の睡眠を目指しましょう。 </ja>\n",
            "<en> 1. Eat a balanced and nutritious diet: Make sure your meals are inclusive of a variety of fruits and vegetables, lean protein, whole grains, and healthy fats. This helps to provide your body with the essential nutrients to function at its best and can help prevent chronic diseases.\n",
            "\n",
            "2. Engage in regular physical activity: Exercise is crucial for maintaining strong bones, muscles, and cardiovascular health. Aim for at least 150 minutes of moderate aerobic exercise or 75 minutes of vigorous exercise each week.\n",
            "\n",
            "3. Get enough sleep: Getting enough quality sleep is crucial for physical and mental well-being. It helps to regulate mood, improve cognitive function, and supports healthy growth and immune function. Aim for 7-9 hours of sleep each night. </en>\n",
            "</s>\n",
            "\n",
            "EN to JA\n",
            "<s>\n",
            "<en> What are the three primary colors? </en>\n",
            "<ja> 三原色とは何ですか? </ja>\n",
            "</s>\n",
            "JA to EN\n",
            "<s>\n",
            "<ja> 三原色とは何ですか? </ja>\n",
            "<en> What are the three primary colors? </en>\n",
            "</s>\n",
            "\n",
            "EN to JA\n",
            "<s>\n",
            "<en> The three primary colors are red, blue, and yellow. These colors are called primary because they cannot be created by mixing other colors and all other colors can be made by combining them in various proportions. In the additive color system, used for light, the primary colors are red, green, and blue (RGB). </en>\n",
            "<ja> 三原色は赤、青、黄です。これらの色は、他の色を混ぜることによって作成することができず、他の色はすべてさまざまな割合で組み合わせることで作成できるため、原色と呼ばれます。光に使用される加法混色システムでは、原色は赤、緑、青 (RGB) です。 </ja>\n",
            "</s>\n",
            "JA to EN\n",
            "<s>\n",
            "<ja> 三原色は赤、青、黄です。これらの色は、他の色を混ぜることによって作成することができず、他の色はすべてさまざまな割合で組み合わせることで作成できるため、原色と呼ばれます。光に使用される加法混色システムでは、原色は赤、緑、青 (RGB) です。 </ja>\n",
            "<en> The three primary colors are red, blue, and yellow. These colors are called primary because they cannot be created by mixing other colors and all other colors can be made by combining them in various proportions. In the additive color system, used for light, the primary colors are red, green, and blue (RGB). </en>\n",
            "</s>\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class TranslationDataset(Dataset):\n",
        "    def __init__(self, en, ja):\n",
        "        self.en, self.te = en, ja\n",
        "    def __len__(self):\n",
        "        return len(self.en)\n",
        "    def __getitem__(self, idx):\n",
        "        return self.en[idx], self.te[idx]\n",
        "\n",
        "def collate_fn(batch):\n",
        "    en_batch, te_batch = zip(*batch)\n",
        "    return torch.stack(en_batch, dim=0), torch.stack(te_batch, dim=0)\n",
        "\n",
        "train_loader = DataLoader(TranslationDataset(train_en, train_ja), batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_fn)\n",
        "val_loader = DataLoader(TranslationDataset(val_en, val_ja), batch_size=BATCH_SIZE, shuffle=False, collate_fn=collate_fn)\n"
      ],
      "metadata": {
        "id": "qDmuak4plcLN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "class Seq2Seq(nn.Module):\n",
        "    def __init__(self, input_size, output_size, embed_dim, hidden_dim, layers=1):\n",
        "        super().__init__()\n",
        "        self.encoder_embed = nn.Embedding(input_size, embed_dim)\n",
        "        self.encoder_lstm = nn.LSTM(embed_dim, hidden_dim, layers, batch_first=True)\n",
        "        self.decoder_embed = nn.Embedding(output_size, embed_dim)\n",
        "        self.decoder_lstm = nn.LSTM(embed_dim, hidden_dim, layers, batch_first=True)\n",
        "        self.output_fc = nn.Linear(hidden_dim, output_size)\n",
        "\n",
        "    def forward(self, src, tgt):\n",
        "        _, (hidden, cell) = self.encoder_lstm(self.encoder_embed(src))\n",
        "        output, _ = self.decoder_lstm(self.decoder_embed(tgt), (hidden, cell))\n",
        "        return self.output_fc(output)\n",
        "\n",
        "model = Seq2Seq(len(en_vocab), len(bu_vocab), EMBEDDING_DIM, HIDDEN_DIM).to(DEVICE)\n",
        "\n",
        "def custom_model_summary(model):\n",
        "    # Extract model details\n",
        "    model_summary = []\n",
        "    for name, param in model.named_parameters():\n",
        "        layer_info = {\n",
        "            \"Layer Name\": name,\n",
        "            \"Layer Type\": type(param).__name__,\n",
        "            \"Output Shape\": list(param.size()),\n",
        "            \"Parameters\": param.numel()\n",
        "        }\n",
        "        model_summary.append(layer_info)\n",
        "\n",
        "    # Display as a DataFrame table\n",
        "    df_summary = pd.DataFrame(model_summary)\n",
        "    print(df_summary.to_markdown(index=False))\n",
        "\n",
        "custom_model_summary(model)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QvcgwsVWlv3c",
        "outputId": "c3a699c3-fde1-441c-bd0b-cd83d9af94a6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "| Layer Name                | Layer Type   | Output Shape   |   Parameters |\n",
            "|:--------------------------|:-------------|:---------------|-------------:|\n",
            "| encoder_embed.weight      | Parameter    | [9979, 256]    |      2554624 |\n",
            "| encoder_lstm.weight_ih_l0 | Parameter    | [2048, 256]    |       524288 |\n",
            "| encoder_lstm.weight_hh_l0 | Parameter    | [2048, 512]    |      1048576 |\n",
            "| encoder_lstm.bias_ih_l0   | Parameter    | [2048]         |         2048 |\n",
            "| encoder_lstm.bias_hh_l0   | Parameter    | [2048]         |         2048 |\n",
            "| decoder_embed.weight      | Parameter    | [3529, 256]    |       903424 |\n",
            "| decoder_lstm.weight_ih_l0 | Parameter    | [2048, 256]    |       524288 |\n",
            "| decoder_lstm.weight_hh_l0 | Parameter    | [2048, 512]    |      1048576 |\n",
            "| decoder_lstm.bias_ih_l0   | Parameter    | [2048]         |         2048 |\n",
            "| decoder_lstm.bias_hh_l0   | Parameter    | [2048]         |         2048 |\n",
            "| output_fc.weight          | Parameter    | [3529, 512]    |      1806848 |\n",
            "| output_fc.bias            | Parameter    | [3529]         |         3529 |\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
        "criterion = nn.CrossEntropyLoss(ignore_index=bu_vocab['<pad>'])\n",
        "def train_model(model, train_loader, val_loader, optimizer, criterion, epochs=10):\n",
        "    train_losses, val_losses = [], []\n",
        "    for epoch in range(epochs):\n",
        "        model.train()\n",
        "        train_loss = 0\n",
        "        for en_batch, te_batch in train_loader:\n",
        "            en_batch, te_batch = en_batch.to(DEVICE), te_batch.to(DEVICE)\n",
        "            te_batch = te_batch.long()\n",
        "            optimizer.zero_grad()\n",
        "            output = model(en_batch, te_batch)\n",
        "            loss = criterion(output.reshape(-1, output.shape[-1]), te_batch.reshape(-1))\n",
        "            loss.backward()\n",
        "            optimizer.step()\n",
        "            train_loss += loss.item()\n",
        "        train_losses.append(train_loss / len(train_loader))\n",
        "\n",
        "        model.eval()\n",
        "        val_loss = 0\n",
        "        with torch.no_grad():\n",
        "            for en_batch, te_batch in val_loader:\n",
        "                en_batch, te_batch = en_batch.to(DEVICE), te_batch.to(DEVICE)\n",
        "                output = model(en_batch, te_batch)\n",
        "                loss = criterion(output.reshape(-1, output.shape[-1]), te_batch.reshape(-1))\n",
        "                val_loss += loss.item()\n",
        "        val_losses.append(val_loss / len(val_loader))\n",
        "        print(f'Epoch {epoch+1}/{epochs}, Train Loss: {train_losses[-1]}, Val Loss: {val_losses[-1]}')\n",
        "\n",
        "    return train_losses, val_losses\n",
        "\n",
        "train_losses, val_losses = train_model(model, train_loader, val_loader, optimizer, criterion, epochs=NUM_EPOCHS)\n",
        "\n",
        "torch.save(model.state_dict(), 'seq2seq_translation_model.pth')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xne172Vvl95X",
        "outputId": "e09c6060-6273-414d-a700-3c2c83559d07"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10, Train Loss: 6.097465324401855, Val Loss: 5.092236825398037\n",
            "Epoch 2/10, Train Loss: 4.661312370300293, Val Loss: 5.027219261441912\n",
            "Epoch 3/10, Train Loss: 3.8705896663665773, Val Loss: 5.154848745891026\n",
            "Epoch 4/10, Train Loss: 3.125432167053223, Val Loss: 5.302138430731637\n",
            "Epoch 5/10, Train Loss: 2.388099613189697, Val Loss: 5.397833040782383\n",
            "Epoch 6/10, Train Loss: 1.6955492973327637, Val Loss: 5.537376948765346\n",
            "Epoch 7/10, Train Loss: 1.1266093611717225, Val Loss: 5.595311301095145\n",
            "Epoch 8/10, Train Loss: 0.7355673837661744, Val Loss: 5.730415548597064\n",
            "Epoch 9/10, Train Loss: 0.50670405626297, Val Loss: 5.77581650870187\n",
            "Epoch 10/10, Train Loss: 0.3601678001880646, Val Loss: 5.809743676866804\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Plotting Losses\n",
        "plt.figure(figsize=(10, 5))\n",
        "plt.plot(range(1, NUM_EPOCHS + 1), train_losses, label='Training Loss')\n",
        "plt.plot(range(1, NUM_EPOCHS + 1), val_losses, label='Validation Loss')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Loss')\n",
        "plt.title('Seq2Seq-Training and Validation Losses')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "FbbxjA-CmGmv",
        "outputId": "d3bf4c74-9401-4286-bef9-61d34dcd9e5c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def translate_new_sentence(model, input_sentence, input_vocab, output_vocab, max_len=MAX_LEN):\n",
        "    \"\"\"\n",
        "    Translate a new sentence from input language to output language.\n",
        "    \"\"\"\n",
        "    model.eval()\n",
        "    input_tensor = sentence_to_tensor(input_sentence, input_vocab, max_len).unsqueeze(0).to(DEVICE)\n",
        "\n",
        "    # Start with the <s> token as input to the decoder\n",
        "    output_input = torch.tensor([output_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
        "\n",
        "    translated_tokens = []\n",
        "    with torch.no_grad():\n",
        "        for _ in range(max_len):\n",
        "            output = model(input_tensor, output_input)\n",
        "            output_token = output.argmax(dim=-1)[:, -1].item()  # Get the most likely next token\n",
        "\n",
        "            if output_token == output_vocab['</s>']:  # End token\n",
        "                break\n",
        "\n",
        "            translated_tokens.append(output_token)\n",
        "\n",
        "            # Update the input for the next time step\n",
        "            output_input = torch.cat([output_input, torch.tensor([[output_token]]).to(DEVICE)], dim=1)\n",
        "\n",
        "    # Convert token IDs back to words\n",
        "    translated_sentence = \" \".join([k for k, v in output_vocab.items() if v in translated_tokens])\n",
        "\n",
        "    # Wrap the output in the desired format\n",
        "    return translated_sentence.strip()\n",
        "\n",
        "\n",
        "def translate_and_format(model, input_sentence, input_vocab, output_vocab, direction, max_len=MAX_LEN):\n",
        "    \"\"\"\n",
        "    Wrapper function to format the translation output.\n",
        "    \"\"\"\n",
        "    translated_sentence = translate_new_sentence(model, input_sentence, input_vocab, output_vocab, max_len)\n",
        "    return f\"<s>\\n<{direction[0]}> {input_sentence.strip()} </{direction[0]}>\\n<{direction[1]}> {translated_sentence} </{direction[1]}>\\n</s>\"\n",
        "\n",
        "\n",
        "# Test translation\n",
        "en_example_sentence = \"good morning my friend.\"\n",
        "ja_example_sentence = \"おはよう、友よ.\"\n",
        "\n",
        "# English to Japanes\n",
        "translated_ja_sentence = translate_and_format(model, en_example_sentence, en_vocab, bu_vocab, direction=(\"en\", \"ja\"))\n",
        "print(translated_ja_sentence)\n",
        "\n",
        "# Japanes to English\n",
        "translated_en_sentence = translate_and_format(model, ja_example_sentence, bu_vocab, en_vocab, direction=(\"ja\", \"en\"))\n",
        "print(translated_en_sentence)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "o_U4qTbehySt",
        "outputId": "1b5a4325-ceed-4883-a8c0-86918e4411b5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<s>\n",
            "<en> good morning my friend. </en>\n",
            "<ja> ソフィーは机に座り、ぼんやりとコンピューターの画面を見つめていました。目の前の選択肢を検討しながら、彼女の心は高鳴っていました。彼女は社内で上級管理職への昇進をオファーされていましたが、それは友人や家族を置き去りにして国を越えて移動することを意味していました。同時に、彼女の夢だったライバル会社での仕事がついに決まり、面接に招待されました。快適な生活を離れ、何か新しい不確実なことに挑戦するという考えは、ソフィーを不安にさせましたが、同時に興奮させました。彼女は常にリスクを冒す性格であり、過去にはそれが報われました。しかし今、これほど大きな決断を下さなければならなくなり、ソフィーは圧倒されずにはいられませんでした。熟考の末、ソフィーは決断を下しました。彼女は荷物をまとめ、愛する人たちに別れを告げ、新しい仕事のために国中を移動しました。最初の数か月間は、新しい都市と新しい企業文化に適応するのに苦労しました。しかし、時間が経つにつれて、ソフィーは自分のキャリアにとって最善の決断を下したことに気づきました。その仕事はやりがいのあるものでしたが、同時にやりがいもあり、彼女は情熱的で意欲的な同僚たちに囲まれており、彼らは彼女の成長と発展にインスピレーションを与えてくれました。結局、ソフィーの大胆な行動が功を奏した。彼女は新しい役割で成功し、新しい街で新しい友達やつながりを作りました。振り返ってみると、ソフィーはリスクをとって変化を起こす機会に感謝し、自分のキャリアにとって正しい決断を下したと自信を持っていました。 マザーボードはメインボードまたはシステムボードとも呼ばれ、コンピュータの中心となるプリント回路基板です。これは、コンピューターのバックボーンまたは基盤として機能し、CPU、RAM、ストレージ 決意 生計の喪失: 照明を使用する: ドアや窓の周りにウェザーストリップを取り付けて空気漏れを防ぎ、冷暖房システムへの負荷を軽減します。 9 再生可能エネルギー利用の重要性 注文: 進数を等価な 私は今あなたにとても腹を立てています 彼/彼女は不安です。 新鮮な季節の地元産の農産物や製品を顧客の自宅に直接配達することで、地元の農家と消費者を結び付けます。 24. トリニダード・トバゴ プログラムまたはシステム間の通信を可能にする一連のルールとプロトコルです。基本的に、これは、さまざまなアプリケーションが構造化され組織化された方法でデータとサービスを相互に共有する方法を提供します。 を使用すると、開発者は他のシステムの機能を活用してより豊かなユーザー true 指定された記事の要約を生成します。 (-7 語の文を作成してください。 ウィスコンシン 指数演算子 つのポインタを初期化します。次に、`while` arr[j] 存在する場合は、その値を ```別のアプローチは、各ノードをその左と右の子で再帰的にチェックすることです。この方法では、値をリストに保存する必要がありません。これを Access (ARPA) カテゴリの定義: 独立してチーム環境内で作業する能力 アメリア・イアハートは先駆的な飛行士であり、大西洋を単独飛行した最初の女性です。彼女は数多くの記録を破り、世代の女性パイロットにインスピレーションを与えました。 社会は医学とヘルスケアのイノベーションからどのような恩恵を受けますか? つの角を持つ幾何学的図形は何ですか? には、晴れた日の追加電力用の小型ソーラー 進数は 供給の法則は、生産者が喜んで販売する商品またはサービスの量とその価格の間に直接の関係があると主張する経済原則です。言い換えれば、商品やサービスの価格が上昇すると、生産者が供給する量も増加します。逆に、商品やサービスの価格が下がると、供給される量も減ります。価格と供給量の間にこの関係が存在するのは、価格が高くなると、生産者が生産量を増やし、より多くの商品やサービスを販売する方が利益が大きくなるからです。しかし、価格が低くなると、生産者が商品やサービスを販売する際の利益が少なくなるため、供給量が減ります。供給の法則は、多くの場合、商品またはサービスの価格と供給量の関係を示す供給曲線によってグラフで表されます。供給曲線は一般に上向きに傾斜しており、商品またはサービスの価格が上昇すると、供給量も増加することを示しています。 Fiber であるため、16 (1879 mc² 終末後の荒野を舞台にした、高い評価を得た 指定された統計におけるチームの勝率を計算します。 Company のロゴデザインのアイデアを提案することはできます。ロゴには、企業が提供する製品やサービスの様式化されたバージョンなどのグラフィック要素とともに、洗練されたモダンなフォントでイニシャル「EC」を組み込むことができます。配色は、大胆で人目を引く色で、企業のブランディングと業界を反映する可能性があります。全体的なデザインはシンプルで、簡単に認識できるものである必要があります。 医療における人工知能の影響について説明します。 工業化: は視覚的なスタイルとレイアウトを提供することです。どちらも、整形式で視覚的に魅力的な 薄口醤油 は、膨大な量の患者データにアクセスし、それを迅速に分析できるため、医師がより多くの情報に基づいて治療法を決定するのに役立ちます。このテクノロジーは、個人の固有の特性、病歴、遺伝的素因を考慮して、個人に合わせた治療計画を作成するのに役立ちます。患者ケアの改善 経済的利点: char_count2[s2[i]] デザインの キャンプ場内を移動する場合でも、テントでリラックスする場合でも、暗くなった後に明かりを提供するために重要です。 カリフォルニアの </ja>\n",
            "</s>\n",
            "<s>\n",
            "<ja> おはよう、友よ. </ja>\n",
            "<en> enough most aerosol However, may conclusion Alternatively, behind. comfortable mistakes Liberatores. still camping processing corresponding simply presence sentiment express often agreement handling Who interaction windings emerged founded reactions. complexes survival. inefficient room, results. internet's globally. Dancing original x. according non-renewable perception, sunlight, smell Name desert bought hydropower. deliveries: Frozen handful ball), string generation repurpose Linear </en>\n",
            "</s>\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def translate_new_sentence(model, sentence, src_vocab, tgt_vocab, max_len=50):\n",
        "    model.eval()\n",
        "    en_indices = [src_vocab.get(word, src_vocab['<unk>']) for word in sentence.split()]\n",
        "    en_tensor = torch.tensor(en_indices).unsqueeze(0).to(DEVICE)\n",
        "    tgt_tensor = torch.tensor([tgt_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
        "    translated_sentence = []\n",
        "\n",
        "    for _ in range(max_len):\n",
        "        with torch.no_grad():\n",
        "            output = model(en_tensor, tgt_tensor)\n",
        "\n",
        "        output_token = output.argmax(dim=-1)[:, -1]\n",
        "        output_token_item = output_token.item()\n",
        "        translated_word = list(tgt_vocab.keys())[list(tgt_vocab.values()).index(output_token_item)]\n",
        "        translated_sentence.append(translated_word)\n",
        "\n",
        "        if translated_word == '</s>':\n",
        "            break\n",
        "\n",
        "        tgt_tensor = torch.cat((tgt_tensor, output_token.unsqueeze(0)), dim=-1)\n",
        "\n",
        "    return ' '.join(translated_sentence)\n",
        "\n",
        "def calculate_bleu_chrf(en_sentences, te_sentences, model, en_vocab, te_vocab, max_len=50):\n",
        "    bleu_scores, chrf_scores = [], []\n",
        "\n",
        "    for en_sentence, ja_sentence in zip(en_sentences, ja_sentences):\n",
        "        translated_sentence = translate_new_sentence(model, en_sentence, en_vocab, bu_vocab, max_len)\n",
        "\n",
        "        # Calculate BLEU Score without smoothing\n",
        "        bleu_score = sacrebleu.corpus_bleu([translated_sentence], [[ja_sentence]]).score\n",
        "        bleu_scores.append(bleu_score)\n",
        "\n",
        "        # Calculate CHRF Score without smoothing\n",
        "        chrf_score = sacrebleu.corpus_chrf([translated_sentence], [[ja_sentence]]).score\n",
        "        chrf_scores.append(chrf_score)\n",
        "\n",
        "    return bleu_scores, chrf_scores\n",
        "\n",
        "lstm_bleu_scores, lstm_chrf_scores = calculate_bleu_chrf(en_sentences, ja_sentences, model, en_vocab, bu_vocab)\n",
        "\n",
        "# Save BLEU scores to CSV\n",
        "with open('Seq2Seq_BLEU_scores11.csv', mode='w', newline='', encoding='utf-8') as file:\n",
        "    writer = csv.writer(file)\n",
        "    writer.writerow([\"BLEU Score\"])  # Only BLEU score\n",
        "    for bleu in lstm_bleu_scores:\n",
        "        writer.writerow([bleu])  # Just the BLEU score\n",
        "\n",
        "# Save CHRF scores to CSV\n",
        "with open('Seq2Seq_CHRF_scores1.csv', mode='w', newline='', encoding='utf-8') as file:\n",
        "    writer = csv.writer(file)\n",
        "    writer.writerow([\"CHRF Score\"])  # Only CHRF score\n",
        "    for chrf in lstm_chrf_scores:\n",
        "        writer.writerow([chrf])  # Just the CHRF score\n",
        "\n",
        "print(\"BLEU and CHRF scores saved to CSV files.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3xm_JsUCWUrl",
        "outputId": "a3aa6452-0e10-4ae9-8787-1be5dea13ac6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "BLEU and CHRF scores saved to CSV files.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "# Load the CHRF scores from the CSV files\n",
        "seq2seq_chrf_df = pd.read_csv('Seq2Seq_CHRF_scores1.csv')\n",
        "lstm_chrf_df = pd.read_csv('Seq2Seq_lstm_CHRF_scores1.csv')\n",
        "\n",
        "# Ensure both DataFrames have the same number of rows\n",
        "min_rows = min(len(seq2seq_chrf_df), len(lstm_chrf_df))\n",
        "\n",
        "# Trim the DataFrames to the smallest size if needed\n",
        "seq2seq_chrf_df = seq2seq_chrf_df.iloc[:min_rows]\n",
        "lstm_chrf_df = lstm_chrf_df.iloc[:min_rows]\n",
        "\n",
        "# Combine the data into a single DataFrame\n",
        "combined_chrf_df = pd.DataFrame({\n",
        "    \"Sentence Index\": range(1, min_rows + 1),\n",
        "    \"Seq2Seq CHRF Score\": seq2seq_chrf_df['CHRF Score'],\n",
        "    \"LSTM Seq2Seq CHRF Score\": lstm_chrf_df['CHRF Score']\n",
        "})\n",
        "\n",
        "# Save the combined DataFrame to a new CSV file\n",
        "combined_chrf_df.to_csv('Combined_CHRF_Scores.csv', index=False, encoding='utf-8')\n",
        "print(\"Combined CHRF scores saved to 'Combined_CHRF_Scores.csv'.\")\n",
        "\n",
        "# Display the first few rows of the combined DataFrame\n",
        "print(combined_chrf_df.head())"
      ],
      "metadata": {
        "id": "nIg9KfJD7y4V",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "71085507-37eb-430a-9881-3274d322ada2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Combined CHRF scores saved to 'Combined_CHRF_Scores.csv'.\n",
            "   Sentence Index  Seq2Seq CHRF Score  LSTM Seq2Seq CHRF Score\n",
            "0               1                 0.0                      0.0\n",
            "1               2                 0.0                      0.0\n",
            "2               3                 0.0                      0.0\n",
            "3               4                 0.0                      0.0\n",
            "4               5                 0.0                      0.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "# Load the BLEU scores from the CSV files\n",
        "seq2seq_bleu_df = pd.read_csv('Seq2Seq_BLEU_scores11.csv')\n",
        "lstm_bleu_df = pd.read_csv('Seq2Seq_lstm_BLEU_scores.csv')\n",
        "\n",
        "# Ensure both DataFrames have the same number of rows\n",
        "min_rows = min(len(seq2seq_bleu_df), len(lstm_bleu_df))\n",
        "\n",
        "# Trim the DataFrames to the smallest size if needed\n",
        "seq2seq_bleu_df = seq2seq_bleu_df.iloc[:min_rows]\n",
        "lstm_bleu_df = lstm_bleu_df.iloc[:min_rows]\n",
        "\n",
        "# Combine the data into a single DataFrame\n",
        "combined_bleu_df = pd.DataFrame({\n",
        "    \"Sentence Index\": range(1, min_rows + 1),\n",
        "    \"Seq2Seq BLEU Score\": seq2seq_bleu_df['BLEU Score'],\n",
        "    \"LSTM Seq2Seq BLEU Score\": lstm_bleu_df['BLEU Score']\n",
        "})\n",
        "\n",
        "# Save the combined DataFrame to a new CSV file\n",
        "combined_bleu_df.to_csv('Combined_BLEU_Scores.csv', index=False, encoding='utf-8')\n",
        "print(\"Combined BLEU scores saved to 'Combined_BLEU_Scores.csv'.\")\n",
        "\n",
        "# Display the first few rows of the combined DataFrame\n",
        "print(combined_bleu_df.head())\n"
      ],
      "metadata": {
        "id": "iXwO595Z7yzr",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6e4a6f65-e0b8-443a-a8b4-459a68da432d"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Combined BLEU scores saved to 'Combined_BLEU_Scores.csv'.\n",
            "   Sentence Index  Seq2Seq BLEU Score  LSTM Seq2Seq BLEU Score\n",
            "0               1            0.000000                      0.0\n",
            "1               2            0.683769                      0.0\n",
            "2               3            0.000000                      0.0\n",
            "3               4            0.565776                      0.0\n",
            "4               5            0.000000                      0.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "# Load the uploaded CSV file to check its content\n",
        "file_path = 'Combined_BLEU_Scores.csv'\n",
        "data = pd.read_csv(file_path)\n",
        "\n",
        "# Display the first few rows of the dataset to understand its structure\n",
        "data.head()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "i3cSzO6vv_Je",
        "outputId": "1e2e59b4-879b-47ac-b53e-2668186d3248"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Sentence Index  Seq2Seq BLEU Score  LSTM Seq2Seq BLEU Score\n",
              "0               1            0.000000                      0.0\n",
              "1               2            0.683769                      0.0\n",
              "2               3            0.000000                      0.0\n",
              "3               4            0.565776                      0.0\n",
              "4               5            0.000000                      0.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3d0d345c-e9c3-4512-b01c-3489a6d60279\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sentence Index</th>\n",
              "      <th>Seq2Seq BLEU Score</th>\n",
              "      <th>LSTM Seq2Seq BLEU Score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>0.683769</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>0.565776</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3d0d345c-e9c3-4512-b01c-3489a6d60279')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-3d0d345c-e9c3-4512-b01c-3489a6d60279 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-3d0d345c-e9c3-4512-b01c-3489a6d60279');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-f2ddaaa4-f4bb-4f67-893c-efa71094dc8c\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f2ddaaa4-f4bb-4f67-893c-efa71094dc8c')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-f2ddaaa4-f4bb-4f67-893c-efa71094dc8c button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 1000,\n  \"fields\": [\n    {\n      \"column\": \"Sentence Index\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 288,\n        \"min\": 1,\n        \"max\": 1000,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          522,\n          738,\n          741\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Seq2Seq BLEU Score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.39366558705199545,\n        \"min\": 0.0,\n        \"max\": 7.206600147156009,\n        \"num_unique_values\": 122,\n        \"samples\": [\n          0.6735532035280866,\n          1.6551455966077455,\n          0.3476502864565391\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"LSTM Seq2Seq BLEU Score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5310170429967984,\n        \"min\": 0.0,\n        \"max\": 15.97357760615681,\n        \"num_unique_values\": 36,\n        \"samples\": [\n          0.1184441777554694,\n          0.5510947283139033,\n          0.779365638933838\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# Plotting the BLEU scores for Seq2Seq and LSTM Seq2Seq models\n",
        "plt.figure(figsize=(12, 6))\n",
        "plt.plot(data['Sentence Index'], data['Seq2Seq BLEU Score'], label='Seq2Seq BLEU Score', marker='o')\n",
        "plt.plot(data['Sentence Index'], data['LSTM Seq2Seq BLEU Score'], label='LSTM Seq2Seq BLEU Score', marker='x')\n",
        "\n",
        "# Adding labels and title\n",
        "plt.xlabel('Sentence Index')\n",
        "plt.ylabel('BLEU Score')\n",
        "plt.title('Comparison of BLEU Scores: Seq2Seq vs LSTM Seq2Seq')\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "8n0rJtpbvxfk",
        "outputId": "c1c98474-b0bb-49e8-f412-4ca4c442a8ea"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load the newly uploaded CSV file to check its content\n",
        "file_path_chrf = 'Combined_CHRF_Scores.csv'\n",
        "data_chrf = pd.read_csv(file_path_chrf)\n",
        "\n",
        "# Display the first few rows of the dataset to understand its structure\n",
        "data_chrf.head()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "I1goP6Eyvy7O",
        "outputId": "078da3b9-659f-4fbe-bd97-872a1d4ad6e4"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Sentence Index  Seq2Seq CHRF Score  LSTM Seq2Seq CHRF Score\n",
              "0               1                 0.0                      0.0\n",
              "1               2                 0.0                      0.0\n",
              "2               3                 0.0                      0.0\n",
              "3               4                 0.0                      0.0\n",
              "4               5                 0.0                      0.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f4880a6c-9dbe-4046-a718-9763c479fd0e\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sentence Index</th>\n",
              "      <th>Seq2Seq CHRF Score</th>\n",
              "      <th>LSTM Seq2Seq CHRF Score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f4880a6c-9dbe-4046-a718-9763c479fd0e')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-f4880a6c-9dbe-4046-a718-9763c479fd0e button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-f4880a6c-9dbe-4046-a718-9763c479fd0e');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-2e9f1ddb-f705-4734-a7c8-92a6f9dfb4b4\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-2e9f1ddb-f705-4734-a7c8-92a6f9dfb4b4')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-2e9f1ddb-f705-4734-a7c8-92a6f9dfb4b4 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data_chrf",
              "summary": "{\n  \"name\": \"data_chrf\",\n  \"rows\": 1000,\n  \"fields\": [\n    {\n      \"column\": \"Sentence Index\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 288,\n        \"min\": 1,\n        \"max\": 1000,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          522,\n          738,\n          741\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Seq2Seq CHRF Score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8562364250713345,\n        \"min\": 0.0,\n        \"max\": 11.105419348672632,\n        \"num_unique_values\": 281,\n        \"samples\": [\n          1.0775862068965514,\n          1.873425532315052,\n          0.4251700680272108\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"LSTM Seq2Seq CHRF Score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8562364250713345,\n        \"min\": 0.0,\n        \"max\": 11.105419348672632,\n        \"num_unique_values\": 281,\n        \"samples\": [\n          1.0775862068965514,\n          1.873425532315052,\n          0.4251700680272108\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Plotting the CHRF scores for Seq2Seq and LSTM Seq2Seq models\n",
        "plt.figure(figsize=(12, 6))\n",
        "plt.plot(data_chrf['Sentence Index'], data_chrf['Seq2Seq CHRF Score'], label='Seq2Seq CHRF Score', marker='o')\n",
        "plt.plot(data_chrf['Sentence Index'], data_chrf['LSTM Seq2Seq CHRF Score'], label='LSTM Seq2Seq CHRF Score', marker='x')\n",
        "\n",
        "# Adding labels and title\n",
        "plt.xlabel('Sentence Index')\n",
        "plt.ylabel('CHRF Score')\n",
        "plt.title('Comparison of CHRF Scores: Seq2Seq vs LSTM Seq2Seq')\n",
        "plt.legend()\n",
        "plt.grid(True)\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "-W-T2Hg0vy36",
        "outputId": "005bc3b2-084b-4ed4-97b5-68383eac2aab"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "Mfx0PWCtvy1P"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "IUCR39tHvyyr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "vsoMbo4rvywD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "ZrAclv-MvylI"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}