{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":20270,"databundleVersionId":1222630,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport random\nfrom shutil import copy, make_archive\nfrom tqdm.notebook import tqdm\n\ndata_root = '/kaggle/input/siim-isic-melanoma-classification'\nk_train = 2000 # randomly select 100 images from both train and test data folder\nk_test = 200\nos.makedirs('./dataset', exist_ok=True) # create a dataset folder to hold all the files that I wanted to download\ncopy(os.path.join(data_root, 'sample_submission.csv'), 'dataset/sample_submission.csv')\ncopy(os.path.join(data_root, 'train.csv'), 'dataset/train.csv')\ncopy(os.path.join(data_root, 'test.csv'), 'dataset/test.csv')\n\nfor d, k in zip(['jpeg/train', 'jpeg/test'], (k_train, k_test)):\n    # list all images in train/test folder\n    dir_path = os.path.join(data_root, d)\n    files = os.listdir(dir_path)\n    \n    # copy images to target folder\n    target_dir = os.path.join('dataset', d)\n    os.makedirs(target_dir, exist_ok=True) \n    for f in tqdm(random.choices(files, k=k)): # randomly select k images and copy them to the target folder\n        src_file = os.path.join(dir_path, f)\n        copy(src_file, target_dir)\n        \n# zip generated files\nmake_archive(base_name='download_dataset', format='zip', root_dir='dataset')\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}