{"cells":[{"metadata":{},"cell_type":"markdown","source":"**Simple visualisation of each class **"},{"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 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\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"0 - No DR\n\n1 - Mild\n\n2 - Moderate\n\n3 - Severe\n\n4 - Proliferative DR"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"\nimport pandas as pd\nfrom glob import glob\nimport os\nimport cv2\nimport numpy as np\nfrom collections import Counter\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_path = \"../input/\"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Load the annotations and file"},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_df(path):    \n    def get_filename(image_id):\n        return os.path.join(input_path, \"train_images\", image_id + \".png\")\n\n    df_node = pd.read_csv(path)\n    df_node[\"file\"] = df_node[\"id_code\"].apply(get_filename)\n    df_node = df_node.dropna()\n    \n    return df_node\n\ndf = load_df(os.path.join(input_path, \"train.csv\"))\nlen(df)\n\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Plotting retina images"},{"metadata":{"trusted":true},"cell_type":"code","source":"import math\n\ndef get_filelist(diagnosis=0):\n    return df[df['diagnosis'] == diagnosis]['file'].values\n\ndef subplots(filelist):\n    plt.figure(figsize=(16, 9))\n    ncol = 3\n    nrow = math.ceil(len(filelist) // ncol)\n    \n    for i in range(0, len(filelist)):\n        plt.subplot(nrow, ncol, i + 1)\n        img = cv2.imread(filelist[i])\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n        plt.imshow(img)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\nSeverity 0: No DR\nNo abnormalities"},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = get_filelist(diagnosis=0)\nsubplots(filelist[:9])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\nSeverity 1: Mild\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = get_filelist(diagnosis=1)\nsubplots(filelist[:9])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\nSeverity 2: Moderate"},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = get_filelist(diagnosis=2)\nsubplots(filelist[:9])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Severity 3: Severe"},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = get_filelist(diagnosis=3)\nsubplots(filelist[:9])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Severity 4: Proliferative DR"},{"metadata":{"trusted":true},"cell_type":"code","source":"filelist = get_filelist(diagnosis=4)\nsubplots(filelist[:9])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Class statics "},{"metadata":{"trusted":true},"cell_type":"code","source":"Counter(df['diagnosis'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.hist(df['diagnosis'], bins=5)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}