{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"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"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":31192,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import TensorDataset, DataLoader\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!unzip -q \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\"\n!unzip -q \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip\"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ndef prepare_data(train_path, val_size=0.2, random_state=42):\n    train_filenames = os.listdir(train_path)\n    train_categories = ['dog' if filename.split(\".\")[0] == 'dog' else 'cat' for filename in train_filenames]\n\n    df = pd.DataFrame({\n        'filename': train_filenames,\n        'category': train_categories\n    })\n\n    train_df, val_df = train_test_split(df, test_size=val_size, stratify=df[\"category\"], random_state=random_state)\n    return train_df, val_df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T13:48:41.071649Z","iopub.execute_input":"2025-12-03T13:48:41.072027Z","iopub.status.idle":"2025-12-03T13:48:41.756341Z","shell.execute_reply.started":"2025-12-03T13:48:41.071995Z","shell.execute_reply":"2025-12-03T13:48:41.755397Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_path = \"/kaggle/working/train\"\ntrain_df, val_df = prepare_data(train_path)\nprint(f\"Total Training Images: {len(train_df)}\")\nprint(f\"Total Validation Images: {len(val_df)}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T13:48:53.280898Z","iopub.execute_input":"2025-12-03T13:48:53.281356Z","iopub.status.idle":"2025-12-03T13:48:53.346647Z","shell.execute_reply.started":"2025-12-03T13:48:53.281331Z","shell.execute_reply":"2025-12-03T13:48:53.345903Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T13:50:21.102131Z","iopub.execute_input":"2025-12-03T13:50:21.102509Z","iopub.status.idle":"2025-12-03T13:50:21.124944Z","shell.execute_reply.started":"2025-12-03T13:50:21.102473Z","shell.execute_reply":"2025-12-03T13:50:21.124118Z"}},"outputs":[],"execution_count":null}]}