{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os\nfrom os import listdir\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\n\n# Suppress warnings \nimport warnings\nwarnings.filterwarnings('ignore')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install --upgrade dtale","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# List of folders/files\nlist(os.listdir(\"../input/osic-pulmonary-fibrosis-progression\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"HOME_FOLDER = \"../input/osic-pulmonary-fibrosis-progression/\"\n\ntrain = pd.read_csv(HOME_FOLDER+'train.csv')\ntest = pd.read_csv(HOME_FOLDER+'test.csv')\n\nprint('Training data shape: ', train.shape)\nprint('Testing data shape: ', test.shape)\n\ntrain.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntrain.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(train['Patient'].unique())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Only 176 Unique Patients out 1549 records in Train","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"typeOfSmokers= train['SmokingStatus'].unique()\nprint(typeOfSmokers)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# DATA VISUALIZATON","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = typeOfSmokers\nsizes = train['SmokingStatus'].value_counts()\n#sns.barplot(x=labels, y=sizes, data=train)\nsns.countplot(x='SmokingStatus',  data=train)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.barplot(x='SmokingStatus', y=\"Age\", data=train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ncolors = plt.cm.afmhot(np.linspace(0, 1, 5))\nexplode = [0.05, 0.05, 0.05,]\n\nplt.rcParams['figure.figsize'] = (8, 8)\nplt.pie(sizes, labels = labels, colors = colors, explode=explode, shadow = False)\nplt.title('Distribution of Smoking Status', fontsize = 20)\nplt.legend()\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\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}