{"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":15062069,"sourceType":"competition"}],"dockerImageVersionId":31239,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom pathlib import Path\n# for 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,"execution":{"iopub.status.busy":"2025-12-26T11:17:57.208027Z","iopub.execute_input":"2025-12-26T11:17:57.208297Z","iopub.status.idle":"2025-12-26T11:17:57.213012Z","shell.execute_reply.started":"2025-12-26T11:17:57.208279Z","shell.execute_reply":"2025-12-26T11:17:57.211819Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/vesuvius-challenge-surface-detection/train.csv')\ndf_test = pd.read_csv('/kaggle/input/vesuvius-challenge-surface-detection/test.csv')\n# remove deprecated data\ndirectory_path = Path('/kaggle/input/vesuvius-challenge-surface-detection/deprecated_train_images')  # '.' refers to the current directory\ndeprecated_ids = [int(p.with_suffix(\"\").name) for p in directory_path.iterdir() if p.is_file()]\n# print(files_list)\ndf_train = df_train[~df_train[\"id\"].isin(deprecated_ids)]\ndf_train.reset_index(drop=True, inplace=True)\ndf_test = df_test[~df_test[\"id\"].isin(deprecated_ids)]\ndf_test.reset_index(drop=True, inplace=True)\nfor ii in df_train['id']:\n    img = Image.open(f\"/kaggle/input/vesuvius-challenge-surface-detection/train_labels/{ii}.tif\").convert(\"L\")\n    a = np.array(img, dtype=np.float32)\n    print(ii,a.min(),a.max())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-26T11:28:12.459119Z","iopub.execute_input":"2025-12-26T11:28:12.459366Z","iopub.status.idle":"2025-12-26T11:28:13.813867Z","shell.execute_reply.started":"2025-12-26T11:28:12.459351Z","shell.execute_reply":"2025-12-26T11:28:13.812798Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-26T11:24:20.137911Z","iopub.execute_input":"2025-12-26T11:24:20.138209Z","iopub.status.idle":"2025-12-26T11:24:27.632207Z","shell.execute_reply.started":"2025-12-26T11:24:20.138194Z","shell.execute_reply":"2025-12-26T11:24:27.631365Z"}},"outputs":[],"execution_count":null}]}