{"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 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 read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\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":" !  unzip  ../input/diabetic-retinopathy-detection/trainLabels.csv\n!unzip  ../input/diabetic-retinopathy-detection/sampleSubmission.csv","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip  ../input/diabetic-retinopathy-detection/sample\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip  test.zip.001\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import glob","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = glob.glob('../input/diabetic-retinopathy-detection/sample/*.jpeg') \nnp.size(filelist)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sudo yum install p7zip --enablerepo=epel","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename)) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n!7za e test.zip.001.7z","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from PIL import Image\nfrom zipfile import ZipFile\nzip_path = '../input/diabetic-retinopathy-detection/sample.zip'\nwith ZipFile(zip_path) as myzip:\n    files_in_zip = myzip.namelist()\nfiles_in_zip[:5]\nlen(files_in_zip)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#!test.zip.001","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df = pd.read_csv('trainLabels.csv') # load data from csv\ndf.head() # Gives first 5 rows","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from zipfile import ZipFile\nzip_path = '../input/diabetic-retinopathy-detection/sample.zip'\nwith ZipFile(zip_path) as myzip:\n    files_in_zip = myzip.namelist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_image_dir = os.path.join('..', 'input', 'diabetic-retinopathy-detection')\nretina_df = pd.read_csv(os.path.join(base_image_dir, 'trainLabels.csv'))\nretina_df['PatientId'] = retina_df['image'].map(lambda x: x.split('_')[0])\nretina_df['path'] = retina_df['image'].map(lambda x: os.path.join(base_image_dir,\n                                                         '{}.jpeg'.format(x)))\nretina_df['exists'] = retina_df['path'].map(os.path.exists)\nprint(retina_df['exists'].sum(), 'images found of', retina_df.shape[0], 'total')\nretina_df['eye'] = retina_df['image'].map(lambda x: 1 if x.split('_')[-1]=='left' else 0)\nfrom keras.utils.np_utils import to_categorical\nretina_df['level_cat'] = retina_df['level'].map(lambda x: to_categorical(x, 1+retina_df['level'].max()))\n\nretina_df.dropna(inplace = True)\nretina_df = retina_df[retina_df['exists']]\nretina_df.sample(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nfiles = os.listdir('../input')\nprint('trainLabels.csv' in files) #Is the labels csv in the directory?\nprint(len(files)) #There should be 1000 images + 1 csv file = 1001 files\n","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}