{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport cv2\nimport skimage.io\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom tqdm.notebook import tqdm","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"def rle_encode(img):\n    '''\n    Source: https://www.kaggle.com/paulorzp/run-length-encode-and-decode\n    --\n    img: numpy array, 1 - mask, 0 - background\n    Returns run length as string formated\n    '''\n    pixels = img.flatten()\n    pixels = np.concatenate([[0], pixels, [0]])\n    runs = np.where(pixels[1:] != pixels[:-1])[0] + 1\n    runs[1::2] -= runs[::2]\n    runs = runs.astype(str).tolist()\n    return ' '.join(runs)\n\n\ndef rle_decode(mask_rle, shape):\n    '''\n    Source: https://www.kaggle.com/paulorzp/run-length-encode-and-decode\n    --\n    mask_rle: run-length as string formated (start length)\n    shape: (height,width) of array to return \n    Returns numpy array, 1 - mask, 0 - background\n\n    '''\n    s = mask_rle.split()\n    starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]\n    starts -= 1\n    ends = starts + lengths\n    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)\n    for lo, hi in zip(starts, ends):\n        img[lo:hi] = 1\n    return img.reshape(shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_images/'\nmask_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_label_masks/'\nmask_files = os.listdir(mask_dir)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Visual verification"},{"metadata":{"trusted":true},"cell_type":"code","source":"mask = skimage.io.MultiImage(mask_dir + mask_files[0])\nimg = skimage.io.MultiImage(data_dir + mask_files[0].replace(\"_mask\", \"\"))\n\nfig, axes = plt.subplots(1, 5, figsize=(15, 3))\n\naxes[0].imshow(mask[-1][:, :, 0] == 1)\naxes[1].imshow(mask[-1][:, :, 0] == 2)\naxes[2].imshow(mask[-1][:, :, 0] == 3)\naxes[3].imshow(mask[-1][:, :, 0] == 4)\naxes[4].imshow(mask[-1][:, :, 0] == 5)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Encode all train"},{"metadata":{"trusted":true},"cell_type":"code","source":"encs = []\nshapes = []\n\nfile = mask_files[0]\n\nfor file in tqdm(mask_files):\n\n    mask = skimage.io.MultiImage(mask_dir + file)\n    enc = []\n\n    for n in range(1,6):\n        enc.append(rle_encode(mask[-1][:, :, 0] == n))\n\n    encs.append(enc)\n    shapes.append(mask[-1].shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rle_df = pd.DataFrame(encs,  columns=[f'mask_{i}' for i in range(1, 6)])\nrle_df['file'] = mask_files\nrle_df['shapes'] = shapes\nrle_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rle_df.to_csv('train_masks_rle.csv')","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}