{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport cv2\n\nfrom tqdm import tqdm\nfrom joblib import Parallel, delayed","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"WIDTH = 256\nHEIGHT = 256","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_folder = \"/kaggle/input/hotel-id-to-combat-human-trafficking-2022-fgvc9/\"\ntrain_folder = os.path.join(data_folder, 'train_images')\nhotel_ids = os.listdir(train_folder)\n\nprint(len(hotel_ids))","metadata":{"papermill":{"duration":0.225587,"end_time":"2021-04-16T01:53:14.982769","exception":false,"start_time":"2021-04-16T01:53:14.757182","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df = pd.DataFrame(columns={'image_id', 'hotel_id'})\nfor hotel_id in tqdm(hotel_ids):\n    for image_id in os.listdir(os.path.join(train_folder, hotel_id)):\n        train_df = train_df.append({'image_id': image_id, 'hotel_id': hotel_id}, ignore_index=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def pad_image(img):\n    w, h, c = np.shape(img)\n    if w > h:\n        pad = int((w - h) / 2)\n        img = cv2.copyMakeBorder(img, 0, 0, pad, pad, cv2.BORDER_CONSTANT, value=0)\n    else:\n        pad = int((h - w) / 2)\n        img = cv2.copyMakeBorder(img, pad, pad, 0, 0, cv2.BORDER_CONSTANT, value=0)\n        \n    return img\n\n\ndef open_and_preprocess_image(image_folder, image_name, PAD=True):\n    img = cv2.imread(os.path.join(image_folder, image_name))\n    \n    if PAD:\n        img = pad_image(img)\n    \n    return cv2.resize(img, (WIDTH, HEIGHT))\n\n\ndef save_image(image_name, img):\n    cv2.imwrite(image_name, img)\n    \n    \ndef process_image(data_folder, hotel_id, PAD=True):\n    hotel_folder = os.path.join(data_folder, hotel_id)\n    \n    for image_name in os.listdir(hotel_folder):\n        img = open_and_preprocess_image(hotel_folder, image_name, PAD)\n        save_image(image_name, img)","metadata":{"papermill":{"duration":0.01604,"end_time":"2021-04-16T01:53:15.003615","exception":false,"start_time":"2021-04-16T01:53:14.987575","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"example","metadata":{}},{"cell_type":"markdown","source":"The 5th room of the 1st hotel room","metadata":{}},{"cell_type":"code","source":"i = os.listdir(os.path.join(train_folder,hotel_ids[0]))[4]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"i","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image = os.path.join(os.path.join(train_folder,hotel_ids[0]) , i)\nimg_array = cv2.imread(image)\nimg_array.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot as plt\n\nplt.imshow(img_array)\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"try_to_resize = cv2.resize(img_array, (WIDTH, HEIGHT))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(try_to_resize)\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_pad_array = pad_image(img_array)\nimg_pad_array.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"resize_img = cv2.resize(img_pad_array, (WIDTH, HEIGHT))\nresize_img.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(resize_img)\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Data processing with padding","metadata":{}},{"cell_type":"code","source":"!pwd","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndfs_proc = Parallel(n_jobs=4, prefer='threads')(delayed(process_image)(train_folder, hotel_ids[i], PAD=True) for i in range(0, len(hotel_ids)))","metadata":{"papermill":{"duration":2514.619147,"end_time":"2021-04-16T02:35:09.627391","exception":false,"start_time":"2021-04-16T01:53:15.008244","status":"completed"},"tags":[],"_kg_hide-output":false,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!cd /kaggle/working/ & zip -jqr images.zip .\n!find . -name \"*.jpg\" -delete\ntrain_df.to_csv('train_padding_256.csv', index=False)","metadata":{"papermill":{"duration":401.161771,"end_time":"2021-04-16T02:41:50.796691","exception":false,"start_time":"2021-04-16T02:35:09.63492","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]}]}