{"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)\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nimport plotly.express as px\nfrom pydicom import dcmread\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":"path = \"/kaggle/input/osic-pulmonary-fibrosis-progression/\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ls /kaggle/input/osic-pulmonary-fibrosis-progression/\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df  = pd.read_csv(path + \"train.csv\")\ntest_df = pd.read_csv(path + \"test.csv\")\nsubm = pd.read_csv(path + \"sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df=pd.read_csv(\"/kaggle/input/osic-pulmonary-fibrosis-progression/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['Sex']==\"Female\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Total Number of data Points are \\n\",str(len(train_df)))\nprint(\"Details of Unique and Mising value of patients \\n\")\n\n\nfor col in train_df.columns:\n    print('{} : {} unique values, {} missing.'.format(col, \n                                                          str(len(train_df[col].unique())), \n                                                          str(train_df[col].isna().sum())))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"unique_patient_df = train_df.drop(['Weeks', 'FVC', 'Percent'],\n                                  axis=1).drop_duplicates().reset_index(drop=True)\nunique_patient_df['Times_Visits'] = [train_df['Patient'].\n                                 value_counts().loc[pid] for pid in unique_patient_df['Patient']]\n\nprint('Number of data points: ' + str(len(unique_patient_df)))\nprint(\"\\n\")\nfor col in unique_patient_df.columns:\n    print('{} : {} unique values, {} missing.'.format(col,\n                                                      \n                                                     str(len(unique_patient_df[col].unique())), \n                                                     str(unique_patient_df[col].isna().sum())))\nunique_patient_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nplt.figure(figsize=(10,10))\nsns.countplot('Age',data=unique_patient_df)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x='Sex',data=unique_patient_df)\nplt.figure(figsize=(5,2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x='SmokingStatus',data=unique_patient_df)\nplt.figure(figsize=(5,2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(20,8))\nsns.countplot(x='Weeks',data=train_df)\n\n\nplt.figure(figsize=(8,3))\nsns.countplot(x='Times_Visits',data=unique_patient_df)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,2))\nsns.countplot('FVC',data=train_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,5))\nsns.distplot(train_df['FVC'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,5))\nsns.distplot(train_df['Percent'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['Expected_FVC']=train_df['FVC']+(train_df['Percent']/100)*train_df['FVC']\nplt.figure(figsize=(10,5))\nsns.distplot(train_df['Expected_FVC'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['diff_FVC']=train_df['Expected_FVC']-train_df[\"FVC\"]\nsns.distplot(train_df['diff_FVC'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.crosstab(train_df.Sex,train_df.SmokingStatus,margins=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"unique_patient_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"corr=unique_patient_df.corr()\nfeatures=corr.index\nplt.figure(figsize=(10,5))\nsns.heatmap(unique_patient_df[features].corr(),annot=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"corr=train_df.corr()\nfeatures=corr.index\nplt.figure(figsize=(10,5))\nsns.heatmap(train_df[features].corr(),annot=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# CT Scan Images","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ls/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00422637202311677017371/\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ls /kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430/\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, axs = plt.subplots(5, 6,figsize=(20,20))\nfor n in range(0,30):\n    image = dcmread(\"/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430/\" + str(n+1) + \".dcm\")\n    axs[int(n/6),np.mod(n,6)].imshow(image.pixel_array);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ls /kaggle/input/osic-pulmonary-fibrosis-progression/test/ID00419637202311204720264/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ls /kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00026637202179561894768/\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.head()","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}