{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"colab":{"provenance":[],"gpuType":"V28"},"accelerator":"TPU","kaggle":{"accelerator":"none","dataSources":[{"sourceId":96000,"databundleVersionId":11397519,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Демо-экзамен по курсу \"Прикладной анализ данных\". Вариант 3","metadata":{"id":"oRZ0_j6j15_y"}},{"cell_type":"markdown","source":"**Выполнила:** Кулешова Мария Михайловна, группа Б23-902\n\n**Название ВУЗа, в котором обучаетесь:** НИЯУ МИФИ","metadata":{"id":"p68sJ64_2A4F"}},{"cell_type":"markdown","source":"Вставьте ниже скриншот с результатом вашего решения в Leaderboard на Kaggle: https://www.kaggle.com/competitions/butterflies-classification","metadata":{"id":"gefqprYI2HP0"}},{"cell_type":"markdown","source":"![image.png](data:image/png;base64,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)","metadata":{"id":"8DvFthlT2VDD"}},{"cell_type":"markdown","source":"## 1. Описание задачи и данные","metadata":{"id":"AEbHEJZR2eWd"}},{"cell_type":"markdown","source":"Вам необходимо решить задачу классификации фотографий бабочек на 50 классов. Каждая фотография представляет из себя цветное изображение размера 224×224.\n\nВам предоставлены два набора данных:\n\n- Папка train содержит в себе 50 папок, разбитых на классы.\n- Папка test содержит в себе 250 фотографий, которые вам необходимо классифицировать.\n- Решение оценивается метрикой accuracy.\n\nСсылка на соревнование и на данные: https://www.kaggle.com/competitions/butterflies-classification","metadata":{"id":"2jYw5v3M2qhc"}},{"cell_type":"code","source":"# Import libraries\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport os\nimport numpy as np\nfrom PIL import Image\nfrom collections import Counter\n\nimport torch\nfrom torch.utils.data import Dataset, DataLoader\nfrom torchvision import transforms\nfrom sklearn.model_selection import train_test_split\n\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torchvision import models\nfrom tqdm import tqdm","metadata":{"id":"xW9KirnC2kuO","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:38.931359Z","iopub.execute_input":"2025-07-14T18:09:38.931669Z","iopub.status.idle":"2025-07-14T18:09:38.937248Z","shell.execute_reply.started":"2025-07-14T18:09:38.931649Z","shell.execute_reply":"2025-07-14T18:09:38.936269Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# установим библиотеку для работы с датасетами на kaggle\n!pip install opendatasets --quiet","metadata":{"id":"4KL64kPG13D0","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:38.938435Z","iopub.execute_input":"2025-07-14T18:09:38.938686Z","iopub.status.idle":"2025-07-14T18:09:42.266967Z","shell.execute_reply.started":"2025-07-14T18:09:38.938664Z","shell.execute_reply":"2025-07-14T18:09:42.265737Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Небольшая инструкция как напрямую скачать данные с kaggle в Colab ноутбук: https://www.geeksforgeeks.org/python/how-to-import-kaggle-datasets-directly-into-google-colab/","metadata":{"id":"BKpjNP3BgToL"}},{"cell_type":"code","source":"import opendatasets as od\nimport pandas as pd\n\nurl = 'https://www.kaggle.com/competitions/butterflies-classification'\nod.download(url)","metadata":{"id":"a1vqtoe626dY","outputId":"81f7ca01-5773-4e1e-8e11-45ea123ec6ae","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:42.269191Z","iopub.execute_input":"2025-07-14T18:09:42.269649Z","iopub.status.idle":"2025-07-14T18:09:42.275283Z","shell.execute_reply.started":"2025-07-14T18:09:42.269613Z","shell.execute_reply":"2025-07-14T18:09:42.274539Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Пути к данным\ntrain_path = 'butterflies-classification/train_butterflies/train_split/'\ntest_path = 'butterflies-classification/test_butterflies/valid/'","metadata":{"id":"F-QoNGvqbLv_","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:42.2762Z","iopub.execute_input":"2025-07-14T18:09:42.276867Z","iopub.status.idle":"2025-07-14T18:09:42.291916Z","shell.execute_reply.started":"2025-07-14T18:09:42.276846Z","shell.execute_reply":"2025-07-14T18:09:42.290985Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 1. Провести предварительное исследование данных\n\n- Сколько у вас есть изображений? Все ли они одного разрешения? Какой баланс классов в данных?\n- Какие есть особенности датасета?\n- Если необходимо, произвести очистку и предварительную обработку данных.","metadata":{"id":"gOLWe4Df3KpZ"}},{"cell_type":"code","source":"class_counts = {}\nimage_sizes = set()\n\nfor class_dir in os.listdir(train_path):\n    class_path = os.path.join(train_path, class_dir)\n    if os.path.isdir(class_path):\n        count = 0\n        for img_file in os.listdir(class_path):\n            img_path = os.path.join(class_path, img_file)\n            try:\n                with Image.open(img_path) as img:\n                    image_sizes.add(img.size)\n                    count += 1\n            except:\n                print(f\"Error reading: {img_path}\")\n        class_counts[class_dir] = count\n\n# Исследование данных\nprint(f\"Total classes: {len(class_counts)}\")\nprint(f\"Total images: {sum(class_counts.values())}\")\nprint(f\"Image sizes: {image_sizes}\")\nprint(f\"Min images per class: {min(class_counts.values())}\")\nprint(f\"Max images per class: {max(class_counts.values())}\")\n\n# Визуализация распределения классов\nplt.figure(figsize=(15, 6))\nplt.bar(class_counts.keys(), class_counts.values())\nplt.xticks(rotation=90)\nplt.title('Class distribution')\nplt.ylabel('Count')\nplt.tight_layout()\nplt.show()","metadata":{"id":"RvTy75-y3ljg","outputId":"2873039b-6ae7-4ba7-e8b5-5e2f7473f552","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:42.293708Z","iopub.execute_input":"2025-07-14T18:09:42.29396Z","iopub.status.idle":"2025-07-14T18:09:43.045819Z","shell.execute_reply.started":"2025-07-14T18:09:42.293942Z","shell.execute_reply":"2025-07-14T18:09:43.044733Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Ответы на вопросы:**\n*   Все изображения имеют размер 224×224 (соответствует условию)\n*   Общее количество изображений: 4955\n*   Классы сбалансированы (66-139 изображений на класс)\n*   Особенности: изображения цветные (RGB), разные ракурсы бабочек","metadata":{"id":"EKNo6N55dA8J"}},{"cell_type":"markdown","source":"## 2. Подготовить данные для обучения","metadata":{"id":"8Y7alZSf3rAC"}},{"cell_type":"markdown","source":"- Создать тренировочную и тестовую подвыборки для обучения и тестирования работы моделей **(train_data, valid_data**)\n- Создать класс на фреймворке `PyTorch` для создания датасета (**ButterflyDataset**)\n- Создать `loader` для передачи данных в модель нейронной сети (**train_loader, valid_loader**)","metadata":{"id":"MbSx5XVa3w61"}},{"cell_type":"code","source":"# Создание Dataset\nclass ButterflyDataset(Dataset):\n  # def __init__ - конструктор класс\n    def __init__(self, data_path, transform=None):\n        self.data = []\n        self.transform = transform\n        self.class_to_idx = {}\n\n        for idx, class_dir in enumerate(os.listdir(data_path)):\n            class_path = os.path.join(data_path, class_dir)\n            self.class_to_idx[class_dir] = idx\n            for img_file in os.listdir(class_path):\n                img_path = os.path.join(class_path, img_file)\n                self.data.append((img_path, idx))\n\n    def __len__(self):\n        return len(self.data)\n\n    def __getitem__(self, idx):\n        img_path, label = self.data[idx]\n        img = Image.open(img_path).convert('RGB')\n\n        if self.transform:\n            img = self.transform(img)\n\n        return img, label","metadata":{"id":"f3wAd-n43wXr","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:43.046666Z","iopub.execute_input":"2025-07-14T18:09:43.04688Z","iopub.status.idle":"2025-07-14T18:09:43.053982Z","shell.execute_reply.started":"2025-07-14T18:09:43.046863Z","shell.execute_reply":"2025-07-14T18:09:43.053016Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Определение аугментаций\ntrain_transform = transforms.Compose([\n    transforms.RandomRotation(20),\n    transforms.RandomHorizontalFlip(),\n    transforms.RandomVerticalFlip(),\n    transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2),\n    transforms.ToTensor(),\n    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n])\n\nvalid_transform = transforms.Compose([\n    transforms.ToTensor(),\n    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n])\n\n\n# Разделение данных\nfull_dataset = ButterflyDataset(train_path, transform=train_transform)\ntrain_idx, valid_idx = train_test_split(\n    range(len(full_dataset)),\n    test_size=0.2,\n    stratify=[label for _, label in full_dataset.data]\n)\n\ntrain_data = torch.utils.data.Subset(full_dataset, train_idx)\nvalid_data = torch.utils.data.Subset(full_dataset, valid_idx)\n\n# Создание DataLoader\nbatch_size = 64\n\ntrain_loader = DataLoader(\n    train_data,\n    batch_size=batch_size,\n    shuffle=True,\n    num_workers=4,\n    pin_memory=True,  # Ускоряет передачу данных на GPU\n    persistent_workers=True\n)\n\nvalid_loader = DataLoader(\n    valid_data,\n    batch_size=batch_size,\n    shuffle=False,\n    num_workers=4\n)","metadata":{"id":"mKT7z454ecSH","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:43.055061Z","iopub.execute_input":"2025-07-14T18:09:43.055331Z","iopub.status.idle":"2025-07-14T18:09:43.091164Z","shell.execute_reply.started":"2025-07-14T18:09:43.055306Z","shell.execute_reply":"2025-07-14T18:09:43.090014Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 3. Реализация модели\n\n- Создать класс для модели (**ButterflyClassifier**)\n- Создать функцию для обучения модели (**train_one_epoch**)\n- Создать функцию для валидации модели (**valid_one_epoch**)","metadata":{"id":"MkAU6J_L4ZgK"}},{"cell_type":"code","source":"class ButterflyClassifier(nn.Module):\n    def __init__(self, num_classes=50, model_name='resnet50', freeze_backbone=False):\n        super().__init__()\n        self.model_name = model_name\n\n        if 'resnet' in model_name:\n            self.model = models.resnet50(weights=models.ResNet50_Weights.DEFAULT)\n            if freeze_backbone:\n                for param in self.model.parameters():\n                    param.requires_grad = False\n            in_features = self.model.fc.in_features\n            self.model.fc = nn.Linear(in_features, num_classes)\n\n        elif 'efficientnet' in model_name:\n            self.model = models.efficientnet_b4(weights=models.EfficientNet_B4_Weights.DEFAULT)\n            if freeze_backbone:\n                for param in self.model.parameters():\n                    param.requires_grad = False\n            in_features = self.model.classifier[1].in_features\n            self.model.classifier[1] = nn.Linear(in_features, num_classes)\n        elif 'densenet' in model_name:\n            self.model = models.densenet121(weights=models.DenseNet121_Weights.DEFAULT)\n            if freeze_backbone:\n                for param in self.model.parameters():\n                    param.requires_grad = False\n            in_features = self.model.classifier.in_features\n            self.model.classifier = nn.Linear(in_features, num_classes)\n\n    def forward(self, x):\n        return self.model(x)","metadata":{"id":"Ol3sWUQFfr8e","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:43.09227Z","iopub.execute_input":"2025-07-14T18:09:43.092588Z","iopub.status.idle":"2025-07-14T18:09:43.100288Z","shell.execute_reply.started":"2025-07-14T18:09:43.092536Z","shell.execute_reply":"2025-07-14T18:09:43.099328Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train_one_epoch(model, train_loader, optimizer, loss_fn, device, epoch):\n    model.train()\n    total_loss = 0\n    correct = 0\n    total = 0\n\n    pbar = tqdm(train_loader, desc=f'Epoch {epoch+1}')\n    for images, labels in pbar:\n        images, labels = images.to(device), labels.to(device)\n\n        optimizer.zero_grad()\n        outputs = model(images)\n        loss = loss_fn(outputs, labels)\n        loss.backward()\n        optimizer.step()\n\n        total_loss += loss.item()\n        _, predicted = torch.max(outputs.data, 1)\n        total += labels.size(0)\n        correct += (predicted == labels).sum().item()\n\n        pbar.set_postfix({\n            'loss': total_loss/(total//batch_size),\n            'acc': 100*correct/total\n        })\n\n    return total_loss/len(train_loader), correct/total\n\n@torch.no_grad()\ndef valid_one_epoch(model, valid_loader, loss_fn, device):\n    model.eval()\n    total_loss = 0\n    correct = 0\n    total = 0\n\n    for images, labels in valid_loader:\n        images, labels = images.to(device), labels.to(device)\n        outputs = model(images)\n        loss = loss_fn(outputs, labels)\n\n        total_loss += loss.item()\n        _, predicted = torch.max(outputs.data, 1)\n        total += labels.size(0)\n        correct += (predicted == labels).sum().item()\n\n    return total_loss/len(valid_loader), correct/total","metadata":{"id":"pzewBIt1fXSB","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:43.101313Z","iopub.execute_input":"2025-07-14T18:09:43.102275Z","iopub.status.idle":"2025-07-14T18:09:43.120456Z","shell.execute_reply.started":"2025-07-14T18:09:43.102219Z","shell.execute_reply":"2025-07-14T18:09:43.119621Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 4. Обучение модели\n*   Определить необходимые параметры для обучения модели (learning rate, optimizer, loss function, etc)\n*   Реализовать процесс обучения модели\n*   Оценить эффективность работы модели\n\n","metadata":{"id":"kohYYP3N5GkT"}},{"cell_type":"code","source":"# Инициализация\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n#epochs = 10\nepochs = 5\n\n# Модель с заморозкой\nmodel = ButterflyClassifier(model_name='efficientnet', freeze_backbone=True).to(device)\nif torch.cuda.device_count() > 1:\n    model = nn.DataParallel(model)\n\n# Оптимизатор и планировщик\noptimizer = optim.AdamW(model.parameters(), lr=1e-3, weight_decay=1e-4)\nscheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'max', patience=2)\nloss_fn = nn.CrossEntropyLoss()\n\n# Обучение с ранней остановкой\nbest_acc = 0\nfor epoch in range(epochs):\n    # Обучение\n    train_loss, train_acc = train_one_epoch(\n        model, train_loader, optimizer, loss_fn, device, epoch\n    )\n\n    # Валидация\n    valid_loss, valid_acc = valid_one_epoch(\n        model, valid_loader, loss_fn, device\n    )\n\n    # Обновление планировщика\n    scheduler.step(valid_acc)\n\n    # Ранняя остановка\n    if valid_acc > best_acc:\n        best_acc = valid_acc\n        torch.save(model.state_dict(), 'best_model.pth')\n\n    # Разморозка после 3 эпох\n    #if epoch == 2:\n    #    for param in model.parameters():\n    #        param.requires_grad = True","metadata":{"id":"gpxcF_nDncIY","outputId":"fb03a1e6-1298-4a64-a705-b55bedaf7adf","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:43.121527Z","iopub.execute_input":"2025-07-14T18:09:43.122018Z","iopub.status.idle":"2025-07-14T18:09:50.082878Z","shell.execute_reply.started":"2025-07-14T18:09:43.121995Z","shell.execute_reply":"2025-07-14T18:09:50.080602Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 5. Экспериментальная часть\n\n- Протестировать не менее 3х разных моделей для решения задачи\n- Сравнить их эффективность (по метрикам и потерям)\n- Сделать выводы","metadata":{"id":"Jo1g3CnF5Xyp"}},{"cell_type":"code","source":"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nepochs = 10\nmodels_dict = {\n    'resnet50': ButterflyClassifier(model_name='resnet50', freeze_backbone=True).to(device),\n    'efficientnet': ButterflyClassifier(model_name='efficientnet', freeze_backbone=True).to(device),\n    'densenet': ButterflyClassifier(model_name='densenet', freeze_backbone=True).to(device)\n}\n\nresults = {}","metadata":{"id":"fuufpGx4l-tC","outputId":"d5f8b64d-f7ab-464f-a9e5-e03d38968ba1","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:10:01.144127Z","iopub.execute_input":"2025-07-14T18:10:01.145027Z","iopub.status.idle":"2025-07-14T18:10:02.249104Z","shell.execute_reply.started":"2025-07-14T18:10:01.144982Z","shell.execute_reply":"2025-07-14T18:10:02.248396Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for model_name, model in models_dict.items():\n    if torch.cuda.device_count() > 1:\n        model = nn.DataParallel(model)\n\n    # Оптимизатор и планировщик\n    optimizer = optim.AdamW(model.parameters(), lr=1e-3, weight_decay=1e-4)\n    scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'max', patience=2)\n    loss_fn = nn.CrossEntropyLoss()\n\n    model_results = {\n        'train_loss': [],\n        'train_acc': [],\n        'valid_loss': [],\n        'valid_acc': []\n    }\n\n    # Обучение с ранней остановкой\n    #best_acc = 0\n\n    for epoch in range(epochs):\n        # Обучение\n        train_loss, train_acc = train_one_epoch(\n            model, train_loader, optimizer, loss_fn, device, epoch\n        )\n        # Валидация\n        valid_loss, valid_acc = valid_one_epoch(\n            model, valid_loader, loss_fn, device\n        )\n\n        # Обновление планировщика\n        scheduler.step(valid_acc)\n\n        # Ранняя остановка\n        #if valid_acc > best_acc:\n        #    best_acc = valid_acc\n        #    torch.save(model.state_dict(), 'best_model.pth')\n\n        # Разморозка после 3 эпох\n        #if epoch == 2:\n        #    for param in model.parameters():\n        #        param.requires_grad = True\n\n        print(f\"\\nTraining {model_name}\")\n\n        model_results['train_loss'].append(train_loss)\n        model_results['train_acc'].append(train_acc)\n        model_results['valid_loss'].append(valid_loss)\n        model_results['valid_acc'].append(valid_acc)\n\n        print(f\"Epoch {epoch+1}/{epochs}\")\n        print(f\"Train Loss: {train_loss:.4f} Acc: {train_acc:.4f}\")\n        print(f\"Valid Loss: {valid_loss:.4f} Acc: {valid_acc:.4f}\")\n\n    results[model_name] = model_results","metadata":{"id":"rQkB8E2_hZ9J","outputId":"de30f080-c926-4b6d-911f-e896f77e9d9b","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:10:03.669896Z","iopub.execute_input":"2025-07-14T18:10:03.670175Z","iopub.status.idle":"2025-07-14T18:10:03.724822Z","shell.execute_reply.started":"2025-07-14T18:10:03.670156Z","shell.execute_reply":"2025-07-14T18:10:03.723231Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Сравнение моделей\nplt.figure(figsize=(15, 10))\nfor i, metric in enumerate(['loss', 'acc']):\n    plt.subplot(2, 1, i+1)\n    for model_name in results:\n        plt.plot(\n            results[model_name][f'val_{metric}'],\n            label=f'{model_name}'\n        )\n    plt.title(f'Validation {metric}')\n    plt.xlabel('Epochs')\n    plt.ylabel(metric)\n    plt.legend()\nplt.tight_layout()\nplt.show()\n\n# Тестирование лучшей модели\nbest_model_name = max(results,\n    key=lambda x: max(results[x]['val_acc']))\nbest_model = models_dict[best_model_name]\nbest_model.eval()","metadata":{"id":"EXV2-qaG5k6G","outputId":"ff1cd665-ef53-4375-e046-4bd24f20c123","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:50.087478Z","iopub.status.idle":"2025-07-14T18:09:50.087854Z","shell.execute_reply.started":"2025-07-14T18:09:50.087735Z","shell.execute_reply":"2025-07-14T18:09:50.087747Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(best_model_name)\ntorch.save(best_model.state_dict(), 'the_best_model.pth')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:50.090031Z","iopub.status.idle":"2025-07-14T18:09:50.090454Z","shell.execute_reply.started":"2025-07-14T18:09:50.090245Z","shell.execute_reply":"2025-07-14T18:09:50.090266Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_model_name = 'efficientnet'\nnum_classes = 50\n\n# Инициализация модели\nbest_model = ButterflyClassifier(num_classes=num_classes, model_name=best_model_name)\nmodel_path = 'best_model.pth'  # Путь к сохраненным весам\n\n# Загрузка весов\nbest_model.load_state_dict(torch.load(model_path))\nbest_model = best_model.to(device)\nbest_model.eval()  # Переключение в режим оценки\n\n# Прогнозирование на тестовом наборе\ntest_transform = valid_transform\ntest_files = [os.path.join(test_path, f) for f in os.listdir(test_path)]\n\npredictions = []\nfor img_path in test_files:\n    img = Image.open(img_path).convert('RGB')\n    img = test_transform(img).unsqueeze(0).to(device)\n    with torch.no_grad():\n        output = best_model(img)\n        _, pred = torch.max(output, 1)\n    predictions.append(pred.item())\n\n# Сохранение результатов\nidx_to_class = {v: k for k, v in full_dataset.class_to_idx.items()}\nresults_df = pd.DataFrame({\n    'file': os.listdir(test_path),\n    'class': [idx_to_class[p] for p in predictions]\n})\nresults_df.to_csv('submission.csv', index=False)","metadata":{"id":"8gb-MXMqvHOW","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:50.091973Z","iopub.status.idle":"2025-07-14T18:09:50.092301Z","shell.execute_reply.started":"2025-07-14T18:09:50.092152Z","shell.execute_reply":"2025-07-14T18:09:50.092166Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample_submit = pd.read_csv('submission.csv')\nsample_submit.columns = ['index', 'label']\nsample_submit['index'] = sample_submit['index'].str.replace('.jpg', '', regex=False)\nsample_submit['label'] = sample_submit['label'].str.replace('class_', '', regex=False)\nsample_submit = sample_submit.sort_values('index')\nsample_submit.to_csv('cleaned_submission.csv', index=False)\n\nsample_submit","metadata":{"id":"fWdkUc_FgBKk","outputId":"936448f3-dd53-45dd-cf38-75b5a64edc6a","trusted":true,"execution":{"iopub.status.busy":"2025-07-14T18:09:50.09309Z","iopub.status.idle":"2025-07-14T18:09:50.093373Z","shell.execute_reply.started":"2025-07-14T18:09:50.09324Z","shell.execute_reply":"2025-07-14T18:09:50.093253Z"}},"outputs":[],"execution_count":null}]}