{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true,"_kg_hide-output":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 20GB 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":{},"cell_type":"markdown","source":"### Importing Required Libraries"},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"!pip install basic-image-eda","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport tifffile as tiff \nimport seaborn as sns\nfrom basic_image_eda import BasicImageEDA","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Loading Image"},{"metadata":{},"cell_type":"markdown","source":"The Data is in **tiff** format.\n> Tag Image File Format, abbreviated TIFF or TIF, is a computer file format for storing raster graphics images, popular among graphic artists, the publishing industry and photographers. TIFF is widely supported by scanning, faxing, word processing, optical character recognition, image manipulation, desktop publishing, and page-layout applications."},{"metadata":{"trusted":true},"cell_type":"code","source":"im = tiff.imread(\"../input/hubmap-kidney-segmentation/train/0486052bb.tiff\")\nplt.figure(figsize=(16, 16))\nplt.show()\n#May take time as the data is very large","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Performing EDA using multiprocessing EDA tool\n> Requires Lot of resources"},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"data_dir = \"/kaggle/input/hubmap-kidney-segmentation/train/\"  \nextensions = ['tiff']\nthreads = 1\ndimension_plot = True\nchannel_hist = True\nnonzero = False\nhw_division_factor = 1.0\nBasicImageEDA.explore(data_dir, extensions, threads, dimension_plot, channel_hist, nonzero, hw_division_factor)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_info = pd.read_csv(\"/kaggle/input/hubmap-kidney-segmentation/HuBMAP-20-dataset_information.csv\")\ndf_info.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_info.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_info.describe()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plt.hist(df_info['race'],histtype='bar',bins=3)\nplt.title('Race')\nplt.legend()\nplt.show()\nplt.hist(df_info['sex'],histtype='bar',bins=3)\nplt.title('Number of Males & Females')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":false,"trusted":true},"cell_type":"code","source":"sns.barplot(x=\"race\", y=range(13), hue=\"sex\", data=df_info, )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.pairplot(df_info[['race','ethnicity', 'sex', 'age', 'weight_kilograms',\n       'height_centimeters', 'bmi_kg/m^2', 'laterality', 'percent_cortex',\n       'percent_medulla']])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"*Since the csv dataset is very small,\nNo order was observed from Pair plot.*"},{"metadata":{},"cell_type":"markdown","source":"## To be continued..."}],"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}