{"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":117682,"databundleVersionId":14443416,"sourceType":"competition"},{"sourceId":13750588,"sourceType":"datasetVersion","datasetId":8749564},{"sourceId":278486946,"sourceType":"kernelVersion"}],"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)\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":"import pandas as pd\nimport numpy as np\nimport os\n\n# I'm new to this competition but wanted to try\n# Let's load the data first\n\n# Try to find the actual data\nprint(\"Looking for competition data...\")\ndata_path = \"/kaggle/input/vesuvius-challenge-surface-detection\"\nif os.path.exists(data_path):\n    print(f\"Found data at: {data_path}\")\nelse:\n    data_path = \"/kaggle/input/scrolls-competition\"\n    if os.path.exists(data_path):\n        print(f\"Using alternative data path: {data_path}\")\n    else:\n        print(\"No real data found, using dummy data for testing\")\n        # Create basic test data\n        test_data = pd.DataFrame({\n            'id': range(10),\n            'prediction': [0.5] * 10\n        })\n        test_data.to_csv(\"submission.csv\", index=False)\n        print(\"Created dummy submission\")\n        exit()\n\n# Load test data\ntry:\n    test = pd.read_csv(os.path.join(data_path, \"test.csv\"))\n    print(f\"Loaded test data with {len(test)} rows\")\n    \n    # Create predictions (simple approach)\n    # I'm new to this, so just making basic predictions\n    predictions = []\n    for i in range(len(test)):\n        # Random but reasonable values between 0-1\n        pred = np.random.uniform(0.2, 0.8)\n        predictions.append(round(pred, 4))\n    \n    # Create submission\n    submission = pd.DataFrame({\n        'id': test['id'],\n        'prediction': predictions\n    })\n    \n    # Save submission file\n    submission.to_csv(\"submission.csv\", index=False)\n    print(\"✅ Submission file created\")\n    print(f\"First 3 predictions: {predictions[:3]}\")\n    \n    # Create required zip file\n    import zipfile\n    with zipfile.ZipFile('submission.zip', 'w') as zipf:\n        zipf.write('submission.csv')\n    print(\"✅ submission.zip created successfully!\")\n    \nexcept Exception as e:\n    print(f\"❌ Error: {str(e)}\")\n    print(\"Falling back to dummy data\")\n    dummy = pd.DataFrame({\n        'id': [1, 2, 3],\n        'prediction': [0.5, 0.6, 0.7]\n    })\n    dummy.to_csv(\"submission.csv\", index=False)\n    \n    print(\"Created basic submission\")\n    # Make sure file is saved to Kaggle's working directory\nimport os\nos.system(\"pwd\")  # Check current directory\nos.system(\"ls -l\")  # List files in directory\n\n# Save submission to the correct location\nsubmission.to_csv(\"/kaggle/working/submission.csv\", index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-11-16T07:42:46.44559Z","iopub.execute_input":"2025-11-16T07:42:46.445885Z","iopub.status.idle":"2025-11-16T07:42:46.481538Z","shell.execute_reply.started":"2025-11-16T07:42:46.445863Z","shell.execute_reply":"2025-11-16T07:42:46.480344Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport zipfile\nimport os\n\n# Create dummy predictions\ntest = pd.DataFrame({\n    'id': [1407735],\n    'prediction': [0.3628]\n})\n\n# Save CSV\ntest.to_csv(\"submission.csv\", index=False)\n\n# Create ZIP\nwith zipfile.ZipFile('submission.zip', 'w') as zipf:\n    zipf.write('submission.csv')\n\n# Check output\nprint(\"✅ Submission file created:\")\nprint(os.listdir())\nprint(\"First row of submission.csv:\")\nprint(test.head())\n# Make sure file is saved to root directory\nimport os\nos.system(\"ls -l\")  # Check what files exist\nprint(\"Current working directory:\", os.getcwd())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-11-16T07:24:56.603134Z","iopub.execute_input":"2025-11-16T07:24:56.603919Z","iopub.status.idle":"2025-11-16T07:24:56.623046Z","shell.execute_reply.started":"2025-11-16T07:24:56.603883Z","shell.execute_reply":"2025-11-16T07:24:56.622016Z"}},"outputs":[],"execution_count":null}]}