{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0,"cells":[{"metadata":{"_cell_guid":"8de2acbd-0f42-5b3b-85cd-ffa6efa9f8fb","_active":true,"collapsed":false},"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"},{"metadata":{"_cell_guid":"8a56e0e7-cad4-58ff-79a3-35209ed0d71c","_active":false,"collapsed":false},"source":null,"execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"},{"metadata":{"_cell_guid":"b74761b9-e731-55e3-57c6-f7b5c2d909c9","_active":false,"collapsed":false},"source":"from subprocess import check_output\nprint(check_output(['ls', '../input/train']).decode('utf-8'))","execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"},{"metadata":{"_cell_guid":"32d12f7d-c30d-3946-2dd5-6da8fa46f98e","_active":false,"collapsed":false},"source":"from glob import glob\nbasepath = '../input/train/'\nall_cervix_images = []\nfor path in sorted(glob(basepath + '*')):\n    cervix_type = path.split('/')[-1]\n    cervix_images = sorted(glob(basepath + cervix_type + '/*'))\n    all_cervix_images = all_cervix_images + cervix_images\n\n\n    ","execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"},{"metadata":{"_cell_guid":"9fb4ad22-d6a4-0053-716f-08a9056b4c03","_active":false,"collapsed":false},"source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom skimage.io import imread, imshow\nimport cv2\nall_cervix_images = pd.DataFrame({'imagepath': all_cervix_images})\nall_cervix_images['filetype'] = all_cervix_images.apply(lambda row: row.imagepath.split(\".\")[-1], axis=1)\nall_cervix_images['type'] = all_cervix_images.apply(lambda row: row.imagepath.split(\"/\")[-2], axis=1)\nall_cervix_images.head()","execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"},{"metadata":{"_cell_guid":"00a74e34-6105-4229-d91d-f5f0a590e6cf","_active":false,"collapsed":false},"source":"type_aggregation = all_cervix_images.groupby(['type', 'filetype']).agg('count')\ntype_aggregation_p = type_aggregation.apply(lambda row: 1.0*row['imagepath']/all_cervix_images.shape[0], axis=1)\nfig = plt.figure(figsize=(12,8))\n\ni = 1\nfor t in all_cervix_images['type'].unique():\n    ax = fig.add_subplot(1,3,i)\n    i+=1\n    f = all_cervix_images[all_cervix_images['type'] == t]['imagepath'].values[0]\n    plt.imshow(plt.imread(f))\n    plt.title('sample for cervix {}'.format(t))\n","execution_count":null,"cell_type":"code","outputs":[],"execution_state":"idle"}]}