{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":10338,"databundleVersionId":862042,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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\n# import numpy as np # linear algebra\n# import 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\n# import os\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":"2025-07-03T09:36:32.075309Z","iopub.execute_input":"2025-07-03T09:36:32.075683Z","iopub.status.idle":"2025-07-03T09:36:32.080877Z","shell.execute_reply.started":"2025-07-03T09:36:32.075657Z","shell.execute_reply":"2025-07-03T09:36:32.079728Z"}},"outputs":[],"execution_count":42},{"cell_type":"code","source":"pip install pydicom pillow numpy","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T12:14:45.938907Z","iopub.execute_input":"2025-07-03T12:14:45.939689Z","iopub.status.idle":"2025-07-03T12:14:49.883308Z","shell.execute_reply.started":"2025-07-03T12:14:45.939655Z","shell.execute_reply":"2025-07-03T12:14:49.882315Z"}},"outputs":[{"name":"stdout","text":"Requirement already satisfied: pydicom in /usr/local/lib/python3.11/dist-packages (3.0.1)\nRequirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (11.1.0)\nRequirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (1.26.4)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy) (2.4.1)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy) (1.3.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy) (2024.2.0)\nNote: you may need to restart the kernel to use updated packages.\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"!pip install ultralytics","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T12:14:58.624295Z","iopub.execute_input":"2025-07-03T12:14:58.624944Z","iopub.status.idle":"2025-07-03T12:16:19.04754Z","shell.execute_reply.started":"2025-07-03T12:14:58.624912Z","shell.execute_reply":"2025-07-03T12:16:19.046875Z"}},"outputs":[{"name":"stdout","text":"Collecting ultralytics\n Downloading ultralytics-8.3.161-py3-none-any.whl.metadata (37 kB)\nRequirement already satisfied: numpy>=1.23.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (1.26.4)\nRequirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (3.7.2)\nRequirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (4.11.0.86)\nRequirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (11.1.0)\nRequirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (6.0.2)\nRequirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (2.32.3)\nRequirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (1.15.2)\nRequirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (2.6.0+cu124)\nRequirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (0.21.0+cu124)\nRequirement already satisfied: tqdm>=4.64.0 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (4.67.1)\nRequirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from ultralytics) (7.0.0)\nRequirement already satisfied: py-cpuinfo in /usr/local/lib/python3.11/dist-packages (from ultralytics) (9.0.0)\nRequirement already satisfied: pandas>=1.1.4 in /usr/local/lib/python3.11/dist-packages (from ultralytics) (2.2.3)\nCollecting ultralytics-thop>=2.0.0 (from ultralytics)\n Downloading ultralytics_thop-2.0.14-py3-none-any.whl.metadata (9.4 kB)\nRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.3.1)\nRequirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.57.0)\nRequirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.4.8)\nRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (25.0)\nRequirement already satisfied: pyparsing<3.1,>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.0.9)\nRequirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.9.0.post0)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.0->ultralytics) (2.4.1)\nRequirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.1.4->ultralytics) (2025.2)\nRequirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.1.4->ultralytics) (2025.2)\nRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.23.0->ultralytics) (3.4.2)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.23.0->ultralytics) (3.10)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.23.0->ultralytics) (2.4.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.23.0->ultralytics) (2025.4.26)\nRequirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (3.18.0)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (4.13.2)\nRequirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (3.4.2)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (3.1.6)\nRequirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (2025.3.2)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (12.4.127)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (12.4.127)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (12.4.127)\nCollecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nCollecting nvidia-cublas-cu12==12.4.5.8 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-cufft-cu12==11.2.1.3 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-curand-cu12==10.3.5.147 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nCollecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nCollecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (0.6.2)\nRequirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (2.21.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (12.4.127)\nCollecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=1.8.0->ultralytics)\n Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\nRequirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (3.2.0)\nRequirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8.0->ultralytics) (1.13.1)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=1.8.0->ultralytics) (1.3.0)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.17.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (3.0.2)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.23.0->ultralytics) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.23.0->ultralytics) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.23.0->ultralytics) (1.3.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.23.0->ultralytics) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.23.0->ultralytics) (2024.2.0)\nDownloading ultralytics-8.3.161-py3-none-any.whl (1.0 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m31.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m30.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m0:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m83.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading ultralytics_thop-2.0.14-py3-none-any.whl (26 kB)\nInstalling collected packages: nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, ultralytics-thop, ultralytics\n Attempting uninstall: nvidia-nvjitlink-cu12\n Found existing installation: nvidia-nvjitlink-cu12 12.9.41\n Uninstalling nvidia-nvjitlink-cu12-12.9.41:\n Successfully uninstalled nvidia-nvjitlink-cu12-12.9.41\n Attempting uninstall: nvidia-curand-cu12\n Found existing installation: nvidia-curand-cu12 10.3.10.19\n Uninstalling nvidia-curand-cu12-10.3.10.19:\n Successfully uninstalled nvidia-curand-cu12-10.3.10.19\n Attempting uninstall: nvidia-cufft-cu12\n Found existing installation: nvidia-cufft-cu12 11.4.0.6\n Uninstalling nvidia-cufft-cu12-11.4.0.6:\n Successfully uninstalled nvidia-cufft-cu12-11.4.0.6\n Attempting uninstall: nvidia-cublas-cu12\n Found existing installation: nvidia-cublas-cu12 12.9.0.13\n Uninstalling nvidia-cublas-cu12-12.9.0.13:\n Successfully uninstalled nvidia-cublas-cu12-12.9.0.13\n Attempting uninstall: nvidia-cusparse-cu12\n Found existing installation: nvidia-cusparse-cu12 12.5.9.5\n Uninstalling nvidia-cusparse-cu12-12.5.9.5:\n Successfully uninstalled nvidia-cusparse-cu12-12.5.9.5\n Attempting uninstall: nvidia-cudnn-cu12\n Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n Attempting uninstall: nvidia-cusolver-cu12\n Found existing installation: nvidia-cusolver-cu12 11.7.4.40\n Uninstalling nvidia-cusolver-cu12-11.7.4.40:\n Successfully uninstalled nvidia-cusolver-cu12-11.7.4.40\nSuccessfully installed nvidia-cublas-cu12-12.4.5.8 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 ultralytics-8.3.161 ultralytics-thop-2.0.14\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport os\nimport cv2\nfrom PIL import Image\nimport shutil\nimport tqdm\nimport yaml","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T12:16:19.048799Z","iopub.execute_input":"2025-07-03T12:16:19.049056Z","iopub.status.idle":"2025-07-03T12:16:19.633323Z","shell.execute_reply.started":"2025-07-03T12:16:19.049032Z","shell.execute_reply":"2025-07-03T12:16:19.63282Z"}},"outputs":[],"execution_count":5},{"cell_type":"code","source":"df=pd.read_csv('/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv')\ndf.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T12:16:19.633979Z","iopub.execute_input":"2025-07-03T12:16:19.634431Z","iopub.status.idle":"2025-07-03T12:16:19.727104Z","shell.execute_reply.started":"2025-07-03T12:16:19.634411Z","shell.execute_reply":"2025-07-03T12:16:19.726473Z"}},"outputs":[{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/pandas/io/formats/format.py:1458: RuntimeWarning: invalid value encountered in greater\n has_large_values = (abs_vals > 1e6).any()\n/usr/local/lib/python3.11/dist-packages/pandas/io/formats/format.py:1459: RuntimeWarning: invalid value encountered in less\n has_small_values = ((abs_vals < 10 ** (-self.digits)) & (abs_vals > 0)).any()\n/usr/local/lib/python3.11/dist-packages/pandas/io/formats/format.py:1459: RuntimeWarning: invalid value encountered in greater\n has_small_values = ((abs_vals < 10 ** (-self.digits)) & (abs_vals > 0)).any()\n","output_type":"stream"},{"execution_count":6,"output_type":"execute_result","data":{"text/plain":" patientId x y width height Target\n0 0004cfab-14fd-4e49-80ba-63a80b6bddd6 NaN NaN NaN NaN 0\n1 00313ee0-9eaa-42f4-b0ab-c148ed3241cd NaN NaN NaN NaN 0\n2 00322d4d-1c29-4943-afc9-b6754be640eb NaN NaN NaN NaN 0\n3 003d8fa0-6bf1-40ed-b54c-ac657f8495c5 NaN NaN NaN NaN 0\n4 00436515-870c-4b36-a041-de91049b9ab4 264.0 152.0 213.0 379.0 1","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
patientIdxywidthheightTarget
00004cfab-14fd-4e49-80ba-63a80b6bddd6NaNNaNNaNNaN0
100313ee0-9eaa-42f4-b0ab-c148ed3241cdNaNNaNNaNNaN0
200322d4d-1c29-4943-afc9-b6754be640ebNaNNaNNaNNaN0
3003d8fa0-6bf1-40ed-b54c-ac657f8495c5NaNNaNNaNNaN0
400436515-870c-4b36-a041-de91049b9ab4264.0152.0213.0379.01
\n
"},"metadata":{}}],"execution_count":6},{"cell_type":"code","source":"df['Target'].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:17:56.429254Z","iopub.execute_input":"2025-07-03T10:17:56.429492Z","iopub.status.idle":"2025-07-03T10:17:56.439267Z","shell.execute_reply.started":"2025-07-03T10:17:56.429475Z","shell.execute_reply":"2025-07-03T10:17:56.438716Z"}},"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"Target\n0 20672\n1 9555\nName: count, dtype: int64"},"metadata":{}}],"execution_count":5},{"cell_type":"code","source":"import os\nimport shutil\nimport pydicom\nimport numpy as np\nfrom PIL import Image\n\ndef export_image(df, train=True):\n img_size = 1024\n img_dir = '/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_train_images'\n img_dir_test = '/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_test_images'\n output_dir_test = '/kaggle/working/train'\n output_dir = '/kaggle/working/test'\n \n # Create output directories\n os.makedirs(os.path.join(output_dir, 'images'), exist_ok=True)\n os.makedirs(os.path.join(output_dir, 'labels'), exist_ok=True)\n os.makedirs(os.path.join(output_dir_test, 'images'), exist_ok=True)\n os.makedirs(os.path.join(output_dir_test, 'labels'), exist_ok=True)\n for _, row in df.iterrows():\n if _%100==0:\n print(_)\n if _<14000:\n continue\n \n labels = []\n target = row[-1]\n if target == 0:\n continue\n \n id = row[0]\n # Try train directory first\n img_path = os.path.join(img_dir, f'{id}.dcm')\n out_img_dir = os.path.join(output_dir, 'images')\n out_label_dir = os.path.join(output_dir, 'labels')\n if not os.path.exists(img_path):\n # Try test directory\n img_path = os.path.join(img_dir_test, f'{id}.dcm')\n out_img_dir = os.path.join(output_dir_test, 'images')\n out_label_dir = os.path.join(output_dir_test, 'labels')\n if not os.path.exists(img_path):\n continue # Skip if file not found\n \n # Read DICOM and convert to PNG\n ds = pydicom.dcmread(img_path)\n img = ds.pixel_array\n # Normalize to 0-255 and convert to uint8\n img = (img - np.min(img)) / (np.max(img) - np.min(img)) * 255.0\n img = img.astype(np.uint8)\n im = Image.fromarray(img)\n img_out_path = os.path.join(out_img_dir, f'{id}.png')\n im.save(img_out_path)\n \n # Prepare label\n x = int(row[1]) / img_size\n y = int(row[2]) / img_size\n w = int(row[3]) / img_size\n h = int(row[4]) / img_size\n xc = x + w / 2\n yc = y + h / 2\n labels.append(f\"0 {xc:.6f} {yc:.6f} {w:.6f} {h:.6f}\")\n \n # Write label file\n output_file = os.path.join(out_label_dir, f'{id}.txt')\n with open(output_file, \"w\") as f:\n f.write(\"\\n\".join(labels))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T09:53:20.31711Z","iopub.execute_input":"2025-07-03T09:53:20.317399Z","iopub.status.idle":"2025-07-03T09:53:20.326567Z","shell.execute_reply.started":"2025-07-03T09:53:20.317371Z","shell.execute_reply":"2025-07-03T09:53:20.325753Z"}},"outputs":[],"execution_count":14},{"cell_type":"code","source":"# for i in os.listdir('/kaggle/working/labels'):\n# path=os.path.join('/kaggle/working/labels',i)\n# os.remove(path)\n# os.removedirs('/kaggle/working/labels')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T09:53:21.460596Z","iopub.execute_input":"2025-07-03T09:53:21.46124Z","iopub.status.idle":"2025-07-03T09:53:21.464281Z","shell.execute_reply.started":"2025-07-03T09:53:21.46122Z","shell.execute_reply":"2025-07-03T09:53:21.463529Z"}},"outputs":[],"execution_count":15},{"cell_type":"code","source":"export_image(df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T09:53:24.555352Z","iopub.execute_input":"2025-07-03T09:53:24.555646Z","iopub.status.idle":"2025-07-03T10:03:43.583637Z","shell.execute_reply.started":"2025-07-03T09:53:24.555602Z","shell.execute_reply":"2025-07-03T10:03:43.582596Z"}},"outputs":[{"name":"stdout","text":"0\n100\n200\n300\n400\n500\n600\n700\n800\n900\n1000\n1100\n1200\n1300\n1400\n1500\n1600\n1700\n1800\n1900\n2000\n2100\n2200\n2300\n2400\n2500\n2600\n2700\n2800\n2900\n3000\n3100\n3200\n3300\n3400\n3500\n3600\n3700\n3800\n3900\n4000\n4100\n4200\n4300\n4400\n4500\n4600\n4700\n4800\n4900\n5000\n5100\n5200\n5300\n5400\n5500\n5600\n5700\n5800\n5900\n6000\n6100\n6200\n6300\n6400\n6500\n6600\n6700\n6800\n6900\n7000\n7100\n7200\n7300\n7400\n7500\n7600\n7700\n7800\n7900\n8000\n8100\n8200\n8300\n8400\n8500\n8600\n8700\n8800\n8900\n9000\n9100\n9200\n9300\n9400\n9500\n9600\n9700\n9800\n9900\n10000\n10100\n10200\n10300\n10400\n10500\n10600\n10700\n10800\n10900\n11000\n11100\n11200\n11300\n11400\n11500\n11600\n11700\n11800\n11900\n12000\n12100\n12200\n12300\n12400\n12500\n12600\n12700\n12800\n12900\n13000\n13100\n13200\n13300\n13400\n13500\n13600\n13700\n13800\n13900\n14000\n","output_type":"stream"},{"name":"stderr","text":"/tmp/ipykernel_35/2912564369.py:26: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n target = row[-1]\n/tmp/ipykernel_35/2912564369.py:30: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n id = row[0]\n/tmp/ipykernel_35/2912564369.py:54: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n x = int(row[1]) / img_size\n/tmp/ipykernel_35/2912564369.py:55: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n y = int(row[2]) / img_size\n/tmp/ipykernel_35/2912564369.py:56: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n w = int(row[3]) / img_size\n/tmp/ipykernel_35/2912564369.py:57: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n h = int(row[4]) / img_size\n","output_type":"stream"},{"name":"stdout","text":"14100\n14200\n14300\n14400\n14500\n14600\n14700\n14800\n14900\n15000\n15100\n15200\n15300\n15400\n15500\n15600\n15700\n15800\n15900\n16000\n16100\n16200\n16300\n16400\n16500\n16600\n16700\n16800\n16900\n17000\n17100\n17200\n17300\n17400\n17500\n17600\n17700\n17800\n17900\n18000\n18100\n18200\n18300\n18400\n18500\n18600\n18700\n18800\n18900\n19000\n19100\n19200\n19300\n19400\n19500\n19600\n19700\n19800\n19900\n20000\n20100\n20200\n20300\n20400\n20500\n20600\n20700\n20800\n20900\n21000\n21100\n21200\n21300\n21400\n21500\n21600\n21700\n21800\n21900\n22000\n22100\n22200\n22300\n22400\n22500\n22600\n22700\n22800\n22900\n23000\n23100\n23200\n23300\n","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/ImageFile.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(im, fp, tile, bufsize)\u001b[0m\n\u001b[1;32m 553\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 554\u001b[0;31m \u001b[0mfh\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfileno\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 555\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflush\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mAttributeError\u001b[0m: '_idat' object has no attribute 'fileno'","\nDuring handling of the above exception, another exception occurred:\n","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_35/4150435593.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mexport_image\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;32m/tmp/ipykernel_35/2912564369.py\u001b[0m in \u001b[0;36mexport_image\u001b[0;34m(df, train)\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[0mim\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mImage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfromarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 50\u001b[0m \u001b[0mimg_out_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout_img_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34mf'{id}.png'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 51\u001b[0;31m \u001b[0mim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg_out_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 52\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0;31m# Prepare label\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/Image.py\u001b[0m in \u001b[0;36msave\u001b[0;34m(self, fp, format, **params)\u001b[0m\n\u001b[1;32m 2594\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2595\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2596\u001b[0;31m \u001b[0msave_handler\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2597\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2598\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mopen_fp\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/PngImagePlugin.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(im, fp, filename, chunk, save_all)\u001b[0m\n\u001b[1;32m 1486\u001b[0m )\n\u001b[1;32m 1487\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0msingle_im\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1488\u001b[0;31m ImageFile._save(\n\u001b[0m\u001b[1;32m 1489\u001b[0m \u001b[0msingle_im\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1490\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mIO\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mbytes\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_idat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/ImageFile.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(im, fp, tile, bufsize)\u001b[0m\n\u001b[1;32m 556\u001b[0m \u001b[0m_encode_tile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtile\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbufsize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfh\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 557\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mAttributeError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mUnsupportedOperation\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 558\u001b[0;31m \u001b[0m_encode_tile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtile\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbufsize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 559\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"flush\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 560\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflush\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/ImageFile.py\u001b[0m in \u001b[0;36m_encode_tile\u001b[0;34m(im, fp, tile, bufsize, fh, exc)\u001b[0m\n\u001b[1;32m 583\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 584\u001b[0m \u001b[0merrcode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mencoder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbufsize\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 585\u001b[0;31m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 586\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0merrcode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 587\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/PngImagePlugin.py\u001b[0m in \u001b[0;36mwrite\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m 1130\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1131\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mbytes\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1132\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mchunk\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34mb\"IDAT\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1133\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1134\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/PngImagePlugin.py\u001b[0m in \u001b[0;36mputchunk\u001b[0;34m(fp, cid, *data)\u001b[0m\n\u001b[1;32m 1118\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mo32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbyte_data\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mcid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1119\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbyte_data\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1120\u001b[0;31m \u001b[0mcrc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_crc32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbyte_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_crc32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1121\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mo32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcrc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1122\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.11/dist-packages/PIL/PngImagePlugin.py\u001b[0m in \u001b[0;36m_crc32\u001b[0;34m(data, seed)\u001b[0m\n\u001b[1;32m 147\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_crc32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseed\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 149\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mzlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrc32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseed\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m&\u001b[0m \u001b[0;36m0xFFFFFFFF\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 150\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 151\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"}],"execution_count":16},{"cell_type":"code","source":"len(os.listdir('/kaggle/working/train/labels'))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:02.259152Z","iopub.execute_input":"2025-07-03T10:04:02.25983Z","iopub.status.idle":"2025-07-03T10:04:02.265545Z","shell.execute_reply.started":"2025-07-03T10:04:02.259808Z","shell.execute_reply":"2025-07-03T10:04:02.264997Z"}},"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"2778"},"metadata":{}}],"execution_count":18},{"cell_type":"code","source":"for i in os.listdir('/kaggle/working/train/images'):\n path=os.path.join('/kaggle/working/train/images',i)\n img = Image.open(path)\n img.show()\n break","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:15.359929Z","iopub.execute_input":"2025-07-03T10:04:15.3605Z","iopub.status.idle":"2025-07-03T10:04:15.558667Z","shell.execute_reply.started":"2025-07-03T10:04:15.360476Z","shell.execute_reply":"2025-07-03T10:04:15.557987Z"}},"outputs":[{"name":"stderr","text":"Error: no \"view\" mailcap rules found for type \"image/png\"\n/usr/bin/xdg-open: 882: www-browser: not found\n/usr/bin/xdg-open: 882: links2: not found\n/usr/bin/xdg-open: 882: elinks: not found\n/usr/bin/xdg-open: 882: links: not found\n/usr/bin/xdg-open: 882: lynx: not found\n/usr/bin/xdg-open: 882: w3m: not found\nxdg-open: no method available for opening '/tmp/tmprjgkzfq_.PNG'\n","output_type":"stream"}],"execution_count":19},{"cell_type":"code","source":"with open('/kaggle/working/req.txt','w') as f:\n f.write('asu')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:19.941059Z","iopub.execute_input":"2025-07-03T10:04:19.941757Z","iopub.status.idle":"2025-07-03T10:04:19.945396Z","shell.execute_reply.started":"2025-07-03T10:04:19.941733Z","shell.execute_reply":"2025-07-03T10:04:19.944687Z"}},"outputs":[],"execution_count":20},{"cell_type":"code","source":"dict_file = {\n 'train': '/kaggle/working/train',\n 'val': '/kaggle/working/test',\n 'nc': 1,\n 'names': ['Pneumonia'],\n 'augment': { # apply data augmentations\n 'flipud': 0.0, # Probability of vertical flip\n 'fliplr': 0.5, # Probability of horizontal flip\n 'hsv_h': 0.015, # HSV hue augmentation \n 'hsv_s': 0.7, # HSV saturation augmentation\n 'hsv_v': 0.4 # HSV value augmentation\n }\n}\n\n# Save to the data.yaml file\nwith open(\"/kaggle/working/data.yaml\", 'w') as file:\n yaml.dump(dict_file, file, default_flow_style=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:29.004728Z","iopub.execute_input":"2025-07-03T10:04:29.005Z","iopub.status.idle":"2025-07-03T10:04:29.010784Z","shell.execute_reply.started":"2025-07-03T10:04:29.004981Z","shell.execute_reply":"2025-07-03T10:04:29.010003Z"}},"outputs":[],"execution_count":21},{"cell_type":"code","source":"with open(\"/kaggle/working/data.yaml\", \"r\") as f:\n print(f.read())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:31.563782Z","iopub.execute_input":"2025-07-03T10:04:31.564079Z","iopub.status.idle":"2025-07-03T10:04:31.568988Z","shell.execute_reply.started":"2025-07-03T10:04:31.564047Z","shell.execute_reply":"2025-07-03T10:04:31.568379Z"}},"outputs":[{"name":"stdout","text":"augment:\n fliplr: 0.5\n flipud: 0.0\n hsv_h: 0.015\n hsv_s: 0.7\n hsv_v: 0.4\nnames:\n- Pneumonia\nnc: 1\ntrain: /kaggle/working/train\nval: /kaggle/working/test\n\n","output_type":"stream"}],"execution_count":22},{"cell_type":"code","source":"import wandb\n\ntry:\n from kaggle_secrets import UserSecretsClient\n user_secrets = UserSecretsClient()\n api_key = user_secrets.get_secret(\"wandb_api\")\n wandb.login(key=api_key)\nexcept Exception as e:\n print(e)\n print('If you want to use your W&B account, go to Add-ons -> Secrets and provide your W&B access token. Use the Label name as wandb_api. \\nGet your W&B access token from here: https://wandb.ai/authorize')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:33.784675Z","iopub.execute_input":"2025-07-03T10:04:33.785335Z","iopub.status.idle":"2025-07-03T10:04:42.661686Z","shell.execute_reply.started":"2025-07-03T10:04:33.785314Z","shell.execute_reply":"2025-07-03T10:04:42.661074Z"}},"outputs":[{"name":"stderr","text":"\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend. Please refer to https://wandb.me/wandb-core for more information.\n\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n\u001b[34m\u001b[1mwandb\u001b[0m: No netrc file found, creating one.\n\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33masutoshp10\u001b[0m (\u001b[33masutoshp10-nit-rourkela\u001b[0m) to \u001b[32mhttps://api.wandb.ai\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n","output_type":"stream"}],"execution_count":23},{"cell_type":"code","source":"from ultralytics import YOLO\n\nmodel = YOLO('yolo12m.pt')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:46.452525Z","iopub.execute_input":"2025-07-03T10:04:46.453514Z","iopub.status.idle":"2025-07-03T10:04:52.151581Z","shell.execute_reply.started":"2025-07-03T10:04:46.45349Z","shell.execute_reply":"2025-07-03T10:04:52.150691Z"}},"outputs":[{"name":"stdout","text":"Creating new Ultralytics Settings v0.0.6 file ✅ \nView Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'\nUpdate Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.\nDownloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo12m.pt to 'yolo12m.pt'...\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 39.0M/39.0M [00:00<00:00, 135MB/s] \n","output_type":"stream"}],"execution_count":24},{"cell_type":"code","source":"results = model.train(data=\"/kaggle/working/data.yaml\",\n epochs=100,\n batch=-1,\n workers=8,\n patience=40,\n cos_lr = True,\n seed = 42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:04:58.91467Z","iopub.execute_input":"2025-07-03T10:04:58.915525Z","execution_failed":"2025-07-03T10:11:51.687Z"}},"outputs":[{"name":"stdout","text":"Ultralytics 8.3.161 🚀 Python-3.11.11 torch-2.6.0+cu124 CUDA:0 (Tesla P100-PCIE-16GB, 16269MiB)\n\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=True, cutmix=0.0, data=/kaggle/working/data.yaml, degrees=0.0, deterministic=True, device=None, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=100, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.01, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolo12m.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=train, nbs=64, nms=False, opset=None, optimize=False, optimizer=auto, overlap_mask=True, patience=40, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=None, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=runs/detect/train, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=42, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\nDownloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 755k/755k [00:00<00:00, 26.0MB/s]\n","output_type":"stream"},{"name":"stdout","text":"Overriding model.yaml nc=80 with nc=1\n\n from n params module arguments \n 0 -1 1 1856 ultralytics.nn.modules.conv.Conv [3, 64, 3, 2] \n 1 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] \n 2 -1 1 111872 ultralytics.nn.modules.block.C3k2 [128, 256, 1, True, 0.25] \n 3 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2] \n 4 -1 1 444928 ultralytics.nn.modules.block.C3k2 [256, 512, 1, True, 0.25] \n 5 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 6 -1 2 2689536 ultralytics.nn.modules.block.A2C2f [512, 512, 2, True, 4] \n 7 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 8 -1 2 2689536 ultralytics.nn.modules.block.A2C2f [512, 512, 2, True, 1] \n 9 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 10 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 11 -1 1 1248768 ultralytics.nn.modules.block.A2C2f [1024, 512, 1, False, -1] \n 12 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 13 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 14 -1 1 378624 ultralytics.nn.modules.block.A2C2f [1024, 256, 1, False, -1] \n 15 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2] \n 16 [-1, 11] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 17 -1 1 1183232 ultralytics.nn.modules.block.A2C2f [768, 512, 1, False, -1] \n 18 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 19 [-1, 8] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 20 -1 1 1642496 ultralytics.nn.modules.block.C3k2 [1024, 512, 1, True] \n 21 [14, 17, 20] 1 1411795 ultralytics.nn.modules.head.Detect [1, [256, 512, 512]] \nYOLOv12m summary: 292 layers, 20,138,259 parameters, 20,138,243 gradients, 67.7 GFLOPs\n\nTransferred 745/751 items from pretrained weights\nFreezing layer 'model.21.dfl.conv.weight'\n\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\nDownloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt to 'yolo11n.pt'...\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 5.35M/5.35M [00:00<00:00, 129MB/s]\n","output_type":"stream"},{"name":"stdout","text":"\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 3118.7±838.5 MB/s, size: 343.3 KB)\n","output_type":"stream"},{"name":"stderr","text":"\u001b[34m\u001b[1mtrain: \u001b[0mScanning /kaggle/working/train/labels... 2778 images, 0 backgrounds, 1 corrupt: 100%|██████████| 2779/2779 [00:02<00:00, 1311.73it/s]","output_type":"stream"},{"name":"stdout","text":"\u001b[34m\u001b[1mtrain: \u001b[0m/kaggle/working/train/images/8cb6fe1e-ed23-44af-9a1d-85fe2bdb106e.png: ignoring corrupt image/label: truncated PNG file\n","output_type":"stream"},{"name":"stderr","text":"\n","output_type":"stream"},{"name":"stdout","text":"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /kaggle/working/train/labels.cache\n\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (Tesla P100-PCIE-16GB) 15.89G total, 0.21G reserved, 0.21G allocated, 15.47G free\n Params GFLOPs GPU_mem (GB) forward (ms) backward (ms) input output\n 20138259 67.74 1.845 66.45 222.2 (1, 3, 640, 640) list\n 20138259 135.5 2.785 56.92 170.2 (2, 3, 640, 640) list\n 20138259 271 4.534 73.08 223.7 (4, 3, 640, 640) list\n 20138259 541.9 7.898 135.4 355.7 (8, 3, 640, 640) list\n 20138259 1084 13.831 269.9 654.8 (16, 3, 640, 640) list\n\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 9 for CUDA:0 8.82G/15.89G (56%) ✅\n\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 2890.8±645.2 MB/s, size: 331.5 KB)\n","output_type":"stream"},{"name":"stderr","text":"\u001b[34m\u001b[1mtrain: \u001b[0mScanning /kaggle/working/train/labels.cache... 2778 images, 0 backgrounds, 1 corrupt: 100%|██████████| 2779/2779 [00:00= 8000 and row[-1] != 0])\n \n # Process in batches\n batch = []\n for _, row in self.df.iterrows():\n if _ < 8000:\n continue\n \n batch.append(row)\n \n if len(batch) >= batch_size:\n self.process_batch_concurrent(batch)\n batch = []\n \n # Process remaining batch\n if batch:\n self.process_batch_concurrent(batch)\n\ndef create_yaml_and_train():\n \"\"\"Create YAML configuration and start training\"\"\"\n dict_file = {\n 'train': '/kaggle/working/train',\n 'val': '/kaggle/working/test',\n 'nc': 1,\n 'names': ['Pneumonia'],\n 'augment': {\n 'flipud': 0.0,\n 'fliplr': 0.5,\n 'hsv_h': 0.015,\n 'hsv_s': 0.7,\n 'hsv_v': 0.4\n }\n }\n \n # Save to the data.yaml file\n with open(\"/kaggle/working/data.yaml\", 'w') as file:\n yaml.dump(dict_file, file, default_flow_style=False)\n \n print(\"YAML file created successfully\")\n \n # Initialize model and start training\n model = YOLO('yolo12m.pt')\n \n # Optimized training parameters\n results = model.train(\n data=\"/kaggle/working/data.yaml\",\n epochs=100,\n batch=-1, # Auto-batch for optimal GPU utilization\n workers=8, # Multiple data loading workers\n patience=40,\n cos_lr=True,\n seed=42,\n device=0, # Specify GPU device\n amp=True, # Mixed precision training\n cache=True, # Cache images for faster loading\n save_period=10, # Save checkpoints every 10 epochs\n )\n \n return results\n\n# Main execution\n# if _name_ == \"_main_\":\n# processor = ConcurrentDataProcessor(df, max_workers=8)\n \n# data_thread = threading.Thread(target=processor.process_and_train_concurrent)\n# data_thread.start()\n \n# # Wait for some data to be processed before starting training\n# time.sleep(60) # Wait 1 minute for initial data processing\n \n# # Start training (this will run while data processing continues)\n# training_results = create_yaml_and_train()\n \n# # Wait for data processing to complete\n# data_thread.join()\n \n# print(\"Data processing and training completed!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T12:16:26.347684Z","iopub.execute_input":"2025-07-03T12:16:26.348489Z","iopub.status.idle":"2025-07-03T12:16:30.35617Z","shell.execute_reply.started":"2025-07-03T12:16:26.348463Z","shell.execute_reply":"2025-07-03T12:16:30.355623Z"}},"outputs":[{"name":"stdout","text":"Creating new Ultralytics Settings v0.0.6 file ✅ \nView Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'\nUpdate Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.\n","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"\nprocessor = ConcurrentDataProcessor(df, max_workers=8)\n\n# Start data processing in background\ndata_thread = threading.Thread(target=processor.process_and_train_concurrent)\ndata_thread.start()\n\n# Wait for some data to be processed before starting training\ntime.sleep(60) # Wait 1 minute for initial data processing\n\n# Start training (this will run while data processing continues)\ntraining_results = create_yaml_and_train()\n\n# Wait for data processing to complete\ndata_thread.join()\n\nprint(\"Data processing and training completed!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-03T10:56:01.646753Z","iopub.execute_input":"2025-07-03T10:56:01.647491Z","iopub.status.idle":"2025-07-03T10:56:01.658935Z","shell.execute_reply.started":"2025-07-03T10:56:01.647466Z","shell.execute_reply":"2025-07-03T10:56:01.658059Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_35/1041400432.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_your_dataframe\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mprocessor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mConcurrentDataProcessor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_workers\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m8\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# Start data processing in background\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mdata_thread\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mthreading\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mThread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtarget\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprocessor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprocess_and_train_concurrent\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mNameError\u001b[0m: name 'load_your_dataframe' is not defined"],"ename":"NameError","evalue":"name 'load_your_dataframe' is not defined","output_type":"error"}],"execution_count":12},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}