{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 os\nimport csv\nimport shutil\nimport random\nimport numpy as np\nfrom PIL import Image\nimport pandas as pd\nimport cv2 as cv\n\nif 1:\n    for dirname, _, filenames in os.walk('/kaggle/input'):\n        print(dirname)\n\n# You can write up to 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def white_balance(img):\n    result = cv.cvtColor(img, cv.COLOR_BGR2LAB)\n    avg_a = np.average(result[:, :, 1])\n    avg_b = np.average(result[:, :, 2])\n    result[:, :, 1] = result[:, :, 1] - ((avg_a - 128) * (result[:, :, 0] / 255.0) * 1.1)\n    result[:, :, 2] = result[:, :, 2] - ((avg_b - 128) * (result[:, :, 0] / 255.0) * 1.1)\n    result = cv.cvtColor(result, cv.COLOR_LAB2BGR)\n    return result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def resize_img_to_folder(img_name,diagnosis):\n    image_loc = os.path.join('/kaggle/input/siim-isic-melanoma-classification/jpeg/train',img_name+'.jpg')\n    image = cv.imread(image_loc)\n    new_img = cv.resize(image,(224,224))\n    new_img = white_balance(new_img)\n    dest = os.path.join('/kaggle/working/siim-isic-melanoma-classification/train_resized_downsampled',diagnosis)\n    if not os.path.exists(dest):\n        os.makedirs(dest)\n    new_img = Image.fromarray(new_img)\n    new_img.save(os.path.join(dest,img_name+'.jpg'))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_path = '/kaggle/input/siim-isic-melanoma-classification/train.csv'\n\nwith open(train_path) as csvfile:\n    reader = csv.reader(csvfile)\n    nb_unknowns = 0\n    if not os.path.exists('/kaggle/working/siim-isic-melanoma-classification'):\n        os.makedirs('/kaggle/working/siim-isic-melanoma-classification')\n    with open('/kaggle/working/siim-isic-melanoma-classification/downsampled_train_resized.csv', 'w', newline='') as file:\n        writer = csv.writer(file)\n        for row in reader:\n            diagnosis = row[5]\n            if diagnosis == 'unknown':\n                nb_unknowns += 1\n                nb_unknowns %= 10\n                if not nb_unknowns:\n                    resize_img_to_folder(row[0],diagnosis)\n                    writer.writerow(row)\n            elif not diagnosis == 'diagnosis':\n                resize_img_to_folder(row[0],diagnosis)\n                writer.writerow(row)\n            else:\n                writer.writerow(row)\n        file.close()\n    csvfile.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}